changed gamma parameter

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfab3bf9e1cd8a35be1c0ca4da0da91022fe394830942f5e1926d6b4643feace
+oid sha256:b20e531e452ee46a704bc6103d8bdfc121aa99ae1d35e07203aa50f3cdd8cc56
 size 1420238

Pyramids/Pyramids-1499904.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c573add8e732a49770adc3bc321069b6fe8b2bbc201741a3c6091a91a834c1e
+size 1420238

Pyramids/Pyramids-1499904.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3934503b8d7e37faecaf297e8b28725bbabd36c8fe601088d3466aa73f77bc2c
+size 8655228

Pyramids/Pyramids-1999887.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24444d542f04406acedd829d09737c881d9615103d53af610de2d386f34128c3
+size 1420238

Pyramids/Pyramids-1999887.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09ff455458162a8fbdfc87027c998e60032a8237c1c59218c28ce79e1479a18
+size 8655228

Pyramids/Pyramids-2499938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcf0cfc8c69ebcda523f702e0dbf68ed68aab44b234dc5c5e1ae94091fb8d19
+size 1420238

Pyramids/Pyramids-2499938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a370bc5ff4bda84eeb5f12d160b0b0c804676952aa9fe22031bdada5433946
+size 8655228

Pyramids/Pyramids-2999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20e531e452ee46a704bc6103d8bdfc121aa99ae1d35e07203aa50f3cdd8cc56
+size 1420238

Pyramids/Pyramids-2999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7556510acf5c0a8ac5baef4d2040fadee55fbc6840297082129fea97fb6dc8
+size 8655228

Pyramids/Pyramids-3000086.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20e531e452ee46a704bc6103d8bdfc121aa99ae1d35e07203aa50f3cdd8cc56
+size 1420238

Pyramids/Pyramids-3000086.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c02967f8be4578dc2f165f5c31188f3a3918aa3170f707e36199d91a26956d
+size 8655228

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5678824c78c93b34d0cf6af81708d3c2733f5440eeeaca8f6407ebdcb0881795
+oid sha256:fbb7b27f97c13cedbc1e303d81167773fa1a2cb3fca8cb2b7051d78ede179728
 size 8654754

Pyramids/events.out.tfevents.1726864335.Spyros.109552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16a2be98b68db026a3638cc25e7b8820f1bddf6bfe7eab07213fea1cbc265b4
+size 784618

config.json

@@ -1 +1 @@
-{"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": 5000000, "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": true, "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": 0.995, "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": 3000000, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -36,7 +36,7 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
       rnd:
-        gamma: 0.99
+        gamma: 0.995
         strength: 0.01
         network_settings:
           normalize: false
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 5000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,8 +82,8 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: true
-  force: false
+  resume: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/smitsis/deep_rl/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/smitsis/deep_rl/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 2 interfaces on host : 0) 10.255.255.254 1) 172.17.157.33
-Multi-casting "[IP] 10.255.255.254 [Port] 55089 [Flags] 2 [Guid] 1991150747 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.17.157.33) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 10.255.255.254 [Port] 55425 [Flags] 2 [Guid] 1894740765 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.17.157.33) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.132 seconds
+- Completed reload, in  0.136 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)
@@ -65,7 +65,7 @@ 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: 1.420981 ms
+UnloadTime: 2.022498 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 10 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3087 frames, [32.0 KB-64.0 KB]: 20950 frames, [64.0 KB-128.0 KB]: 13473 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7854 frames, [32.0 KB-64.0 KB]: 31630 frames, [64.0 KB-128.0 KB]: 16783 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
@@ -81,7 +81,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 18]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
@@ -183,11 +183,6 @@ PlayerConnection::CleanupMemory Statistics:
       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 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -198,9 +193,9 @@ PlayerConnection::CleanupMemory Statistics:
       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
+    [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_EnlightenWorker] x 10
@@ -213,6 +208,11 @@ PlayerConnection::CleanupMemory Statistics:
       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_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
@@ -261,7 +261,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -294,28 +294,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 30 frames, [1.0 MB-2.0 MB]: 37481 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55969 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.1 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 1930
+  Peak main deferred allocation count 13352
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 2.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37510 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56267 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 25.5 MB
+      Peak Block count 3
+      Peak Allocated memory 30.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 37511 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 28.5 MB
+      Peak Allocated memory 31.1 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -342,15 +342,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 2.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 37510 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56267 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 37511 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -360,15 +360,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 2.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 40 frames, [1.0 MB-2.0 MB]: 37471 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55969 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 37510 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56267 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -378,21 +378,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 2.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 37511 frames
+      Peak usage frame count: [0-1.0 KB]: 56268 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]: 37511 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56268 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [32.0 KB-64.0 KB]: 37511 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 56268 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 43.8 KB
@@ -401,4 +401,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1726861732560,"processId":86828,"allocatedMemory":2209098,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":227599},{"Thread":34964},{"Manager":26827},{"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":3542},{"DynamicArray":30868},{"HashMap":7680},{"Utility":8704},{"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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1726868382424,"processId":109613,"allocatedMemory":2209098,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":227599},{"Thread":34964},{"Manager":26827},{"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":3542},{"DynamicArray":30868},{"HashMap":7680},{"Utility":8704},{"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.16470925509929657,
-            "min": 0.1543617993593216,
-            "max": 0.2311645895242691,
-            "count": 66
+            "value": 0.1341688632965088,
+            "min": 0.13263465464115143,
+            "max": 1.3872299194335938,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5007.1611328125,
-            "min": 4539.4716796875,
-            "max": 6997.134765625,
-            "count": 66
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 227.90076335877862,
-            "min": 204.4,
-            "max": 297.88461538461536,
-            "count": 66
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29855.0,
-            "min": 27484.0,
-            "max": 31641.0,
-            "count": 66
+            "value": 4033.65283203125,
+            "min": 3955.69580078125,
+            "max": 42083.0078125,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 4979960.0,
-            "min": 3029963.0,
-            "max": 4979960.0,
-            "count": 66
+            "value": 2999958.0,
+            "min": 29952.0,
+            "max": 2999958.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 4979960.0,
-            "min": 3029963.0,
-            "max": 4979960.0,
-            "count": 66
+            "value": 2999958.0,
+            "min": 29952.0,
+            "max": 2999958.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7946914434432983,
-            "min": 0.6763219833374023,
-            "max": 0.8943750262260437,
-            "count": 66
+            "value": 0.8524944186210632,
+            "min": -0.10985395312309265,
+            "max": 0.9063270688056946,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 236.81805419921875,
-            "min": 192.75177001953125,
-            "max": 279.0450134277344,
-            "count": 66
+            "value": 261.7157897949219,
+            "min": -26.364948272705078,
+            "max": 276.42974853515625,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.003992420621216297,
-            "min": -0.005213670898228884,
-            "max": 0.013375768437981606,
-            "count": 66
+            "value": 0.012428520247340202,
+            "min": -0.02336515486240387,
+            "max": 0.8881713151931763,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.1897413730621338,
-            "min": -1.5484602451324463,
-            "max": 3.999354839324951,
-            "count": 66
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7415572421923848,
-            "min": 1.6077807510558229,
-            "max": 1.7938561522184986,
-            "count": 66
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 228.14399872720242,
-            "min": 167.20919810980558,
-            "max": 261.9029982239008,
-            "count": 66
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7415572421923848,
-            "min": 1.6077807510558229,
-            "max": 1.7938561522184986,
-            "count": 66
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 228.14399872720242,
-            "min": 167.20919810980558,
-            "max": 261.9029982239008,
-            "count": 66
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.009061433341723373,
-            "min": 0.00832925945301817,
-            "max": 0.012428955118660021,
-            "count": 66
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 1.1870477677657618,
-            "min": 1.065525280610018,
-            "max": 1.4051403166195087,
-            "count": 66
+            "value": 3.8155558109283447,
+            "min": -6.892720699310303,
+            "max": 213.16111755371094,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06678107167157658,
-            "min": 0.06424657277901398,
-            "max": 0.07329772362191718,
-            "count": 66
+            "value": 0.06472630039068117,
+            "min": 0.06252626269062082,
+            "max": 0.07702694473929982,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9349350034020723,
-            "min": 0.8994520189061956,
-            "max": 1.0867753221554106,
-            "count": 66
+            "value": 0.9061682054695364,
+            "min": 0.5132823468026392,
+            "max": 1.0936694837000687,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01587486903619964,
-            "min": 0.010914587446285285,
-            "max": 0.01610098868522549,
-            "count": 66
+            "value": 0.0154032837772753,
+            "min": 0.00036945041838324136,
+            "max": 0.021864434819524593,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22224816650679496,
-            "min": 0.15280422424799397,
-            "max": 0.234270447779529,
-            "count": 66
+            "value": 0.2156459728818542,
+            "min": 0.004433405020598896,
+            "max": 0.23363027764043734,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.061377884335713e-06,
-            "min": 2.061377884335713e-06,
-            "max": 0.0001190496388882357,
-            "count": 66
+            "value": 1.5772494742833342e-06,
+            "min": 1.5772494742833342e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 2.8859290380699984e-05,
-            "min": 2.8859290380699984e-05,
-            "max": 0.0016666949444352997,
-            "count": 66
+            "value": 2.208149263996668e-05,
+            "min": 2.208149263996668e-05,
+            "max": 0.0039825916724695,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10068709285714286,
-            "min": 0.10068709285714286,
-            "max": 0.13968319285714287,
-            "count": 66
+            "value": 0.10052571666666668,
+            "min": 0.10052571666666668,
+            "max": 0.19946118095238097,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4096193000000001,
-            "min": 1.4096193000000001,
-            "max": 2.05047086,
-            "count": 66
+            "value": 1.4073600333333336,
+            "min": 1.3897045333333333,
+            "max": 2.8275305,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 7.864057642857141e-05,
-            "min": 7.864057642857141e-05,
-            "max": 0.0039743509664285715,
-            "count": 66
+            "value": 6.251909500000004e-05,
+            "min": 6.251909500000004e-05,
+            "max": 0.009946171977142856,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0011009680699999998,
-            "min": 0.0011009680699999998,
-            "max": 0.055640913529999995,
-            "count": 66
+            "value": 0.0008752673300000005,
+            "min": 0.0008752673300000005,
+            "max": 0.13277029695,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.003794910619035363,
-            "min": 0.0035534801427274942,
-            "max": 0.004355163313448429,
-            "count": 66
+            "value": 0.008665002882480621,
+            "min": 0.008133871480822563,
+            "max": 0.6720296740531921,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.05312874913215637,
-            "min": 0.04974872246384621,
-            "max": 0.06444988399744034,
-            "count": 66
+            "value": 0.1213100403547287,
+            "min": 0.1168643906712532,
+            "max": 4.704207897186279,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 202.43243243243242,
+            "min": 192.05369127516778,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29960.0,
+            "min": 15984.0,
+            "max": 33179.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7964093855163394,
+            "min": -1.0000000521540642,
+            "max": 1.7964093855163394,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 267.6649984419346,
+            "min": -32.000001668930054,
+            "max": 267.6649984419346,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7964093855163394,
+            "min": -1.0000000521540642,
+            "max": 1.7964093855163394,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 267.6649984419346,
+            "min": -32.000001668930054,
+            "max": 267.6649984419346,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.018090883511526434,
+            "min": 0.01724788235937799,
+            "max": 15.016267117112875,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.695541643217439,
+            "min": 2.4515712619468104,
+            "max": 240.260273873806,
+            "count": 100
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 66
+            "count": 100
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 66
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1726859090",
+        "start_time_seconds": "1726864333",
         "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
-        "command_line_arguments": "/home/smitsis/deep_rl/unit5/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
+        "command_line_arguments": "/home/smitsis/deep_rl/unit5/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1726861732"
+        "end_time_seconds": "1726868382"
     },
-    "total": 2642.6037404359995,
+    "total": 4049.3710773970015,
     "count": 1,
-    "self": 0.7807197000001906,
+    "self": 0.5895341570030723,
     "children": {
         "run_training.setup": {
-            "total": 0.025233232998289168,
+            "total": 0.03725820699764881,
             "count": 1,
-            "self": 0.025233232998289168
+            "self": 0.03725820699764881
         },
         "TrainerController.start_learning": {
-            "total": 2641.797787503001,
+            "total": 4048.744285033001,
             "count": 1,
-            "self": 2.459813700614177,
+            "self": 3.717256762243778,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8511594330011576,
+                    "total": 3.4224397639991366,
                     "count": 1,
-                    "self": 2.8511594330011576
+                    "self": 3.4224397639991366
                 },
                 "TrainerController.advance": {
-                    "total": 2636.4056767233815,
-                    "count": 131575,
-                    "self": 2.1113766945782118,
+                    "total": 4041.477001824758,
+                    "count": 195656,
+                    "self": 3.3308607920771465,
                     "children": {
                         "env_step": {
-                            "total": 1566.6334122156004,
-                            "count": 131575,
-                            "self": 1393.7164908044906,
+                            "total": 2328.007386639303,
+                            "count": 195656,
+                            "self": 2055.21509451999,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 171.41549694276182,
-                                    "count": 131575,
-                                    "self": 6.609550149114511,
+                                    "total": 270.5359504977714,
+                                    "count": 195656,
+                                    "self": 10.361718275496969,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 164.8059467936473,
-                                            "count": 125034,
-                                            "self": 164.8059467936473
+                                            "total": 260.17423222227444,
+                                            "count": 187558,
+                                            "self": 260.17423222227444
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.5014244683479774,
-                                    "count": 131575,
+                                    "total": 2.256341621541651,
+                                    "count": 195656,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2638.5324067147085,
-                                            "count": 131575,
+                                            "total": 4043.7644807621546,
+                                            "count": 195656,
                                             "is_parallel": true,
-                                            "self": 1407.2050894831773,
+                                            "self": 2240.803112125108,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0058036119989992585,
+                                                            "total": 0.0027552920000744052,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0015641659956600051,
+                                                            "self": 0.0007699239940848202,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004239446003339253,
+                                                                    "total": 0.001985368005989585,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004239446003339253
+                                                                    "self": 0.001985368005989585
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0359110450008302,
+                                                            "total": 0.030666878999909386,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00017528400348965079,
+                                                            "self": 0.0002245820032840129,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002970570021716412,
+                                                                    "total": 0.00014396199912880547,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002970570021716412
+                                                                    "self": 0.00014396199912880547
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03497489899746142,
+                                                                    "total": 0.029428026999084977,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03497489899746142
+                                                                    "self": 0.029428026999084977
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0004638049977074843,
+                                                                    "total": 0.0008703079984115902,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00011666199861792848,
+                                                                    "self": 0.00020219699581502937,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0003471429990895558,
+                                                                            "total": 0.0006681110025965609,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0003471429990895558
+                                                                            "self": 0.0006681110025965609
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1231.3273172315312,
-                                                    "count": 131574,
+                                                    "total": 1802.9613686370467,
+                                                    "count": 195655,
                                                     "is_parallel": true,
-                                                    "self": 23.82499154812467,
+                                                    "self": 36.88238994132553,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.233260555123707,
-                                                            "count": 131574,
+                                                            "total": 34.78763833605626,
+                                                            "count": 195655,
                                                             "is_parallel": true,
-                                                            "self": 22.233260555123707
+                                                            "self": 34.78763833605626
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1111.0648670323353,
-                                                            "count": 131574,
+                                                            "total": 1616.0866041508634,
+                                                            "count": 195655,
                                                             "is_parallel": true,
-                                                            "self": 1111.0648670323353
+                                                            "self": 1616.0866041508634
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 74.2041980959475,
-                                                            "count": 131574,
+                                                            "total": 115.20473620880148,
+                                                            "count": 195655,
                                                             "is_parallel": true,
-                                                            "self": 18.177741283903742,
+                                                            "self": 28.329421952494158,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 56.02645681204376,
-                                                                    "count": 1052592,
+                                                                    "total": 86.87531425630732,
+                                                                    "count": 1565240,
                                                                     "is_parallel": true,
-                                                                    "self": 56.02645681204376
+                                                                    "self": 86.87531425630732
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1067.6608878132029,
-                            "count": 131575,
-                            "self": 4.730437471502228,
+                            "total": 1710.138754393378,
+                            "count": 195656,
+                            "self": 7.325309896543331,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 175.63756949370145,
-                                    "count": 131575,
-                                    "self": 175.31443521670008,
+                                    "total": 267.4758459489276,
+                                    "count": 195656,
+                                    "self": 266.97439568792106,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.32313427700137254,
-                                            "count": 4,
-                                            "self": 0.32313427700137254
+                                            "total": 0.5014502610065392,
+                                            "count": 6,
+                                            "self": 0.5014502610065392
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 887.2928808479992,
-                                    "count": 945,
-                                    "self": 430.8011253907389,
+                                    "total": 1435.337598547907,
+                                    "count": 1395,
+                                    "self": 682.9063918591346,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 456.4917554572603,
-                                            "count": 45504,
-                                            "self": 456.4917554572603
+                                            "total": 752.4312066887724,
+                                            "count": 68319,
+                                            "self": 752.4312066887724
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.570023055654019e-07,
+                    "total": 8.700008038431406e-07,
                     "count": 1,
-                    "self": 8.570023055654019e-07
+                    "self": 8.700008038431406e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0811367890019028,
+                    "total": 0.12758581199886976,
                     "count": 1,
-                    "self": 0.0017935910036612768,
+                    "self": 0.011729711997759296,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07934319799824152,
+                            "total": 0.11585610000111046,
                             "count": 1,
-                            "self": 0.07934319799824152
+                            "self": 0.11585610000111046
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 3499928,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3499928.onnx",
-                "reward": 1.7284999750554562,
-                "creation_time": 1726859738.8496764,
+                "steps": 1499904,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499904.onnx",
+                "reward": 1.7683333158493042,
+                "creation_time": 1726866256.9976497,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3499928.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499904.pt"
                 ]
             },
             {
-                "steps": 3999957,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3999957.onnx",
-                "reward": 1.4953200086951255,
-                "creation_time": 1726860374.4547257,
+                "steps": 1999887,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999887.onnx",
+                "reward": 1.840500008314848,
+                "creation_time": 1726867096.5587735,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-3999957.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999887.pt"
                 ]
             },
             {
-                "steps": 4499925,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4499925.onnx",
-                "reward": 1.7916666467984517,
-                "creation_time": 1726861116.4773228,
+                "steps": 2499938,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499938.onnx",
+                "reward": 1.815999972820282,
+                "creation_time": 1726867742.5966105,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-4499925.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499938.pt"
                 ]
             },
             {
-                "steps": 4999883,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-4999883.onnx",
-                "reward": 1.7923999965190887,
-                "creation_time": 1726861731.777334,
+                "steps": 2999958,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999958.onnx",
+                "reward": 1.8352500032633543,
+                "creation_time": 1726868381.8447685,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-4999883.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2999958.pt"
                 ]
             },
             {
-                "steps": 5000011,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-5000011.onnx",
-                "reward": 1.7923999965190887,
-                "creation_time": 1726861731.8658853,
+                "steps": 3000086,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000086.onnx",
+                "reward": 1.8352500032633543,
+                "creation_time": 1726868381.9737666,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-5000011.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-3000086.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 5000011,
+            "steps": 3000086,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7923999965190887,
-            "creation_time": 1726861731.8658853,
+            "reward": 1.8352500032633543,
+            "creation_time": 1726868381.9737666,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-5000011.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000086.pt"
             ]
         }
     },