Second Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af69796cfbe5dcab2581d6806fd587097d65ff17ffb8655bdf541beda06fa8c
+size 1420238

Pyramids/Pyramids-1000161.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af69796cfbe5dcab2581d6806fd587097d65ff17ffb8655bdf541beda06fa8c
+size 1420238

Pyramids/Pyramids-1000161.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbcf60ac21889b57c9f845c64538eab1729699096bae43e856fab4dc89fe3e7
+size 8655228

Pyramids/Pyramids-499883.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61e100438f818ec0029ff48285b0d5c6ec499b967eb45e193f06193b80ce6bd
+size 1420238

Pyramids/Pyramids-499883.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71619bd3f9bce209b17114751a12899f6e0ff948c83ed8bd0253eab9a527a0e6
+size 8655149

Pyramids/Pyramids-999905.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af69796cfbe5dcab2581d6806fd587097d65ff17ffb8655bdf541beda06fa8c
+size 1420238

Pyramids/Pyramids-999905.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af121659b04fd664d553576ddcaa271bf167b88d45802ebc31e07977b85744bd
+size 8655149

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3284f046d83432d372a4bb20599444d164ebeed56a66033ff2db16e66e839a
+size 8654754

Pyramids/events.out.tfevents.1729578248.debian.1105774.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da52cf5eda1448d4f602dd31e0996fb4cbdc156d4c1c825458302fde8402db7
+size 324001

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: ml-agents
 tags:
-- SnowballTarget
+- Pyramids
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-SnowballTarget
+- ML-Agents-Pyramids
 ---
 
-  # **ppo** Agent playing **SnowballTarget**
-  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
   ## Usage (with ML-Agents)

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -1,12 +1,12 @@
 default_settings: null
 behaviors:
-  SnowballTarget:
+  Pyramids:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.01
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 50000
+    checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -35,17 +35,30 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
     init_path: null
-    keep_checkpoints: 10
+    keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 200000
-    time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -66,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: Pyramids Training
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,14 @@
-Mono path[0] = '/home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 10.0.0.17
+Multi-casting "[IP] 10.0.0.17 [Port] 55378 [Flags] 2 [Guid] 3593283327 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.0.0.17) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/luser/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /home/luser/.config/unity3d/Hugging Face/SnowballTarget
+PlayerPrefs - Creating folder: /home/luser/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/luser/.config/unity3d/Unity Technologies/UnityEnvironment
 Unable to load player prefs
-Initialize engine version: 2021.3.14f1 (eee1884e7226)
-[Subsystems] Discovering subsystems at path /home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/luser/projects/hugFace/mlTest/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -14,10 +16,24 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.065 seconds
+- Completed reload, in  0.074 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
@@ -25,105 +41,112 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.520747 ms
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.743730 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 4 worker threads for Enlighten.
-Memory Statistics:
+PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2415 frames, [32.0 KB-64.0 KB]: 12369 frames, [64.0 KB-128.0 KB]: 3981 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 252 B
-      Overflow Count 0
-    [ALLOC_TEMP_Loading.PreloadManager]
-      Initial Block Size 256.0 KB
-      Current Block Size 304.0 KB
-      Peak Allocated Bytes 228.9 KB
-      Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 5]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 4]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 3]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 12]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker] x 4
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 1]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -143,58 +166,79 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_BatchDeleteObjects]
+    [ALLOC_TEMP_EnlightenWorker] x 4
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 44
+  Peak main deferred allocation count 12984
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18762 frames, [32.0 MB-64.0 MB]: 3 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.9 MB
+      Peak Block count 3
+      Peak Allocated memory 33.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 24.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -221,52 +265,63 @@ Memory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4243 frames, [64.0 KB-128.0 KB]: 1220 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 39.6 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
 [ALLOC_CACHEOBJECTS] Dual Thread Allocator
-  Peak main deferred allocation count 0
+  Peak main deferred allocation count 1
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.6 MB
+      Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18765 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 2.2 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.0 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5463 frames
+      Peak usage frame count: [0-1.0 KB]: 18766 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18766 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.7 KB
+      Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18766 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 31.4 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1729579761947,"processId":1105847,"allocatedMemory":2169425,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":205998},{"Thread":34628},{"Manager":13967},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3562},{"DynamicArray":30868},{"HashMap":7680},{"Utility":3808},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -1,214 +1,250 @@
 {
     "name": "root",
     "gauges": {
-        "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.002143383026123,
-            "min": 1.002143383026123,
-            "max": 2.8694119453430176,
-            "count": 20
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.30786994099617004,
+            "min": 0.3035747706890106,
+            "max": 1.4912446737289429,
+            "count": 33
         },
-        "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9623.5830078125,
-            "min": 9623.5830078125,
-            "max": 29511.90234375,
-            "count": 20
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 9309.9873046875,
+            "min": 9097.5283203125,
+            "max": 45238.3984375,
+            "count": 33
         },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.mean": {
+            "value": 989960.0,
+            "min": 29952.0,
+            "max": 989960.0,
+            "count": 33
         },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+        "Pyramids.Step.sum": {
+            "value": 989960.0,
+            "min": 29952.0,
+            "max": 989960.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.56418228149414,
-            "min": 0.32530006766319275,
-            "max": 12.56418228149414,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6741190552711487,
+            "min": -0.12404728680849075,
+            "max": 0.6829549074172974,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2450.015625,
-            "min": 63.10821533203125,
-            "max": 2518.0478515625,
-            "count": 20
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 188.0792236328125,
+            "min": -29.399206161499023,
+            "max": 198.16934204101562,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.02373865246772766,
+            "min": 0.008841241709887981,
+            "max": 0.30106568336486816,
+            "count": 33
         },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 20
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 6.62308406829834,
+            "min": 2.484388828277588,
+            "max": 71.35256958007812,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06578948340657186,
-            "min": 0.061012868139739884,
-            "max": 0.07526436924401386,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.0679078684827976,
+            "min": 0.06455739669004532,
+            "max": 0.07298525753486458,
+            "count": 33
         },
-        "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2631579336262874,
-            "min": 0.24405147255895954,
-            "max": 0.3730850697508739,
-            "count": 20
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9507101587591665,
+            "min": 0.5102156544396594,
+            "max": 1.0677580084302463,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1957122599158217,
-            "min": 0.10599944498230174,
-            "max": 0.29366141849873106,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015231617565968053,
+            "min": 0.0011841848847443024,
+            "max": 0.01725753505130694,
+            "count": 33
         },
-        "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7828490396632868,
-            "min": 0.42399777992920695,
-            "max": 1.4683070924936554,
-            "count": 20
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21324264592355274,
+            "min": 0.015394403501675931,
+            "max": 0.24160549071829712,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.720233140907144e-06,
+            "min": 7.720233140907144e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
-        "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010808326397270001,
+            "min": 0.00010808326397270001,
+            "max": 0.0035084648305117997,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10257337857142856,
+            "min": 0.10257337857142856,
+            "max": 0.19838354285714285,
+            "count": 33
         },
-        "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4360273,
+            "min": 1.3886848,
+            "max": 2.5694882000000003,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002670805192857144,
+            "min": 0.0002670805192857144,
+            "max": 0.00983851593142857,
+            "count": 33
         },
-        "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0037391272700000016,
+            "min": 0.0037391272700000016,
+            "max": 0.11697187118000002,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.931818181818183,
-            "min": 2.727272727272727,
-            "max": 24.931818181818183,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.013592837378382683,
+            "min": 0.013592837378382683,
+            "max": 0.34104791283607483,
+            "count": 33
         },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1097.0,
-            "min": 120.0,
-            "max": 1368.0,
-            "count": 20
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.19029971957206726,
+            "min": 0.19029971957206726,
+            "max": 2.3873353004455566,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.931818181818183,
-            "min": 2.727272727272727,
-            "max": 24.931818181818183,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 282.5925925925926,
+            "min": 270.67543859649123,
+            "max": 999.0,
+            "count": 33
         },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1097.0,
-            "min": 120.0,
-            "max": 1368.0,
-            "count": 20
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30520.0,
+            "min": 15984.0,
+            "max": 33018.0,
+            "count": 33
         },
-        "SnowballTarget.IsTraining.mean": {
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6618388624930824,
+            "min": -1.0000000521540642,
+            "max": 1.714514831210127,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 179.4785971492529,
+            "min": -29.613001704216003,
+            "max": 193.14219836890697,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6618388624930824,
+            "min": -1.0000000521540642,
+            "max": 1.714514831210127,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 179.4785971492529,
+            "min": -29.613001704216003,
+            "max": 193.14219836890697,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03944893315228573,
+            "min": 0.03944893315228573,
+            "max": 6.222614713013172,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 4.260484780446859,
+            "min": 4.260484780446859,
+            "max": 99.56183540821075,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         },
-        "SnowballTarget.IsTraining.sum": {
+        "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1729576612",
+        "start_time_seconds": "1729578247",
         "python_version": "3.10.12 (main, Jun 12 2024, 02:25:10) [GCC 12.2.0]",
-        "command_line_arguments": "/home/luser/.pyenv/versions/3.10.12/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/home/luser/.pyenv/versions/3.10.12/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.1+cu118",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1729576930"
+        "end_time_seconds": "1729579761"
     },
-    "total": 317.8528209384531,
+    "total": 1514.490784265101,
     "count": 1,
-    "self": 0.2201411183923483,
+    "self": 0.2753289267420769,
     "children": {
         "run_training.setup": {
-            "total": 0.1493026465177536,
+            "total": 0.1496268454939127,
             "count": 1,
-            "self": 0.1493026465177536
+            "self": 0.1496268454939127
         },
         "TrainerController.start_learning": {
-            "total": 317.483377173543,
+            "total": 1514.065828492865,
             "count": 1,
-            "self": 0.4942772537469864,
+            "self": 1.5539047848433256,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.2777200918644667,
+                    "total": 1.2428660988807678,
                     "count": 1,
-                    "self": 1.2777200918644667
+                    "self": 1.2428660988807678
                 },
                 "TrainerController.advance": {
-                    "total": 315.65588099882007,
-                    "count": 18208,
-                    "self": 0.24032771959900856,
+                    "total": 1511.2102739587426,
+                    "count": 64366,
+                    "self": 1.4706240259110928,
                     "children": {
                         "env_step": {
-                            "total": 315.41555327922106,
-                            "count": 18208,
-                            "self": 231.51014351658523,
+                            "total": 878.23102789931,
+                            "count": 64366,
+                            "self": 780.5239738970995,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 83.67387328110635,
-                                    "count": 18208,
-                                    "self": 1.1666073575615883,
+                                    "total": 96.79489367455244,
+                                    "count": 64366,
+                                    "self": 3.9262360762804747,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 82.50726592354476,
-                                            "count": 18208,
-                                            "self": 82.50726592354476
+                                            "total": 92.86865759827197,
+                                            "count": 62553,
+                                            "self": 92.86865759827197
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.23153648152947426,
-                                    "count": 18208,
+                                    "total": 0.9121603276580572,
+                                    "count": 64366,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 316.96725662238896,
-                                            "count": 18208,
+                                            "total": 1511.9636805150658,
+                                            "count": 64366,
                                             "is_parallel": true,
-                                            "self": 172.4194098226726,
+                                            "self": 831.167067700997,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0015680287033319473,
+                                                            "total": 0.0015347693115472794,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000452972948551178,
+                                                            "self": 0.0004483480006456375,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0011150557547807693,
-                                                                    "count": 10,
+                                                                    "total": 0.0010864213109016418,
+                                                                    "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0011150557547807693
+                                                                    "self": 0.0010864213109016418
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.024469077587127686,
+                                                            "total": 0.027647079899907112,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003335755318403244,
+                                                            "self": 0.00038668327033519745,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00023067928850650787,
+                                                                    "total": 0.0002905502915382385,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00023067928850650787
+                                                                    "self": 0.0002905502915382385
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.022788627073168755,
+                                                                    "total": 0.025971844792366028,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.022788627073168755
+                                                                    "self": 0.025971844792366028
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0011161956936120987,
+                                                                    "total": 0.0009980015456676483,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002922993153333664,
+                                                                    "self": 0.0002583600580692291,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0008238963782787323,
-                                                                            "count": 10,
+                                                                            "total": 0.0007396414875984192,
+                                                                            "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0008238963782787323
+                                                                            "self": 0.0007396414875984192
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 144.54784679971635,
-                                                    "count": 18207,
+                                                    "total": 680.7966128140688,
+                                                    "count": 64365,
                                                     "is_parallel": true,
-                                                    "self": 6.313228230923414,
+                                                    "self": 20.55948062799871,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 4.166642235592008,
-                                                            "count": 18207,
+                                                            "total": 18.758210077881813,
+                                                            "count": 64365,
                                                             "is_parallel": true,
-                                                            "self": 4.166642235592008
+                                                            "self": 18.758210077881813
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 112.24370483122766,
-                                                            "count": 18207,
+                                                            "total": 577.9006294813007,
+                                                            "count": 64365,
                                                             "is_parallel": true,
-                                                            "self": 112.24370483122766
+                                                            "self": 577.9006294813007
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 21.82427150197327,
-                                                            "count": 18207,
+                                                            "total": 63.57829262688756,
+                                                            "count": 64365,
                                                             "is_parallel": true,
-                                                            "self": 4.9589143972843885,
+                                                            "self": 15.513901114463806,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 16.865357104688883,
-                                                                    "count": 182070,
+                                                                    "total": 48.064391512423754,
+                                                                    "count": 514920,
                                                                     "is_parallel": true,
-                                                                    "self": 16.865357104688883
+                                                                    "self": 48.064391512423754
                                                                 }
                                                             }
                                                         }
@@ -305,53 +341,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 0.00019265525043010712,
-                    "count": 1,
-                    "self": 0.00019265525043010712,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 631.5086220335215,
+                            "count": 64366,
+                            "self": 2.8546887040138245,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 315.1159566491842,
-                                    "count": 150643,
-                                    "is_parallel": true,
-                                    "self": 2.5816312804818153,
+                                "process_trajectory": {
+                                    "total": 107.28508945927024,
+                                    "count": 64366,
+                                    "self": 107.15276909433305,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 170.72974267043173,
-                                            "count": 150643,
-                                            "is_parallel": true,
-                                            "self": 170.22571489028633,
-                                            "children": {
-                                                "RLTrainer._checkpoint": {
-                                                    "total": 0.5040277801454067,
-                                                    "count": 4,
-                                                    "is_parallel": true,
-                                                    "self": 0.5040277801454067
-                                                }
-                                            }
-                                        },
-                                        "_update_policy": {
-                                            "total": 141.80458269827068,
-                                            "count": 90,
-                                            "is_parallel": true,
-                                            "self": 38.252048183232546,
-                                            "children": {
-                                                "TorchPPOOptimizer.update": {
-                                                    "total": 103.55253451503813,
-                                                    "count": 4587,
-                                                    "is_parallel": true,
-                                                    "self": 103.55253451503813
-                                                }
-                                            }
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.13232036493718624,
+                                            "count": 2,
+                                            "self": 0.13232036493718624
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 521.3688438702375,
+                                    "count": 454,
+                                    "self": 265.2426653560251,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 256.12617851421237,
+                                            "count": 22770,
+                                            "self": 256.12617851421237
                                         }
                                     }
                                 }
@@ -359,15 +375,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 9.462237358093262e-07,
+                    "count": 1,
+                    "self": 9.462237358093262e-07
+                },
                 "TrainerController._save_models": {
-                    "total": 0.055306173861026764,
+                    "total": 0.058782704174518585,
                     "count": 1,
-                    "self": 0.0007705632597208023,
+                    "self": 0.0010871011763811111,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.05453561060130596,
+                            "total": 0.057695602998137474,
                             "count": 1,
-                            "self": 0.05453561060130596
+                            "self": 0.057695602998137474
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,59 +1,41 @@
 {
-    "SnowballTarget": {
+    "Pyramids": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.0,
-                "creation_time": 1729576692.5220191,
+                "steps": 499883,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499883.onnx",
+                "reward": 1.9119999408721924,
+                "creation_time": 1729578983.1287463,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499883.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.727272727272727,
-                "creation_time": 1729576769.864294,
+                "steps": 999905,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999905.onnx",
+                "reward": 1.7299999843041103,
+                "creation_time": 1729579761.612024,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-999905.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.545454545454547,
-                "creation_time": 1729576849.267738,
+                "steps": 1000161,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000161.onnx",
+                "reward": 1.7299999843041103,
+                "creation_time": 1729579761.693063,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
-                ]
-            },
-            {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.272727272727273,
-                "creation_time": 1729576930.1697712,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.272727272727273,
-                "creation_time": 1729576930.2463071,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000161.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.272727272727273,
-            "creation_time": 1729576930.2463071,
+            "steps": 1000161,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.7299999843041103,
+            "creation_time": 1729579761.693063,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000161.pt"
             ]
         }
     },