Hugging Face's logo

YoavWigelman
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
YoavWigelman commited on
Commit
cd389d3
•
1 Parent(s): 3639580

Second Push

Browse files
Files changed (20) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-198499942.onnx +3 -0
  3. SoccerTwos/SoccerTwos-198499942.pt +3 -0
  4. SoccerTwos/SoccerTwos-198999874.onnx +3 -0
  5. SoccerTwos/SoccerTwos-198999874.pt +3 -0
  6. SoccerTwos/SoccerTwos-199499942.onnx +3 -0
  7. SoccerTwos/SoccerTwos-199499942.pt +3 -0
  8. SoccerTwos/SoccerTwos-199999836.onnx +3 -0
  9. SoccerTwos/SoccerTwos-199999836.pt +3 -0
  10. SoccerTwos/SoccerTwos-200000490.onnx +3 -0
  11. SoccerTwos/SoccerTwos-200000490.pt +3 -0
  12. SoccerTwos/checkpoint.pt +1 -1
  13. SoccerTwos/events.out.tfevents.1687874269.tensorado.174517.0 +3 -0
  14. SoccerTwos/events.out.tfevents.1687925091.tensorado.230230.0 +3 -0
  15. SoccerTwos/events.out.tfevents.1688012069.tensorado.344496.0 +3 -0
  16. config.json +1 -1
  17. configuration.yaml +7 -7
  18. run_logs/Player-0.log +16 -16
  19. run_logs/timers.json +194 -194
  20. run_logs/training_status.json +24 -24
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ea75c1ad800a656cf05ba80f36c90ce1b1bd94783814de317e6904b61b2595c
3
  size 1764633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd0a08f220dbab7f00c9dc94fb410af805f095930a25ce2309e205bedb506d9
3
  size 1764633
SoccerTwos/SoccerTwos-198499942.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df4d817edbfe9efa854a9175d5c3638c862be8c216bb82be21be3ff5c7f0dcb
3
+ size 1764633
SoccerTwos/SoccerTwos-198499942.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefee69889b0563628f0bb5c9672e4f78e636edc95f471bfd9d879ebfa62c503
3
+ size 28422481
SoccerTwos/SoccerTwos-198999874.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465deab64d18027e0931af3563aae0b156712f1cf4c1ef8433194187c1a5caa8
3
+ size 1764633
SoccerTwos/SoccerTwos-198999874.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ccefb25dba60c82209b3c821e7f5a59620f16fd86b591b73202ac7e4693b97
3
+ size 28422481
SoccerTwos/SoccerTwos-199499942.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798bfb682bc16df64f5e5b8cb1fff936afe733663b0a7ab7820b93c3911e57ec
3
+ size 1764633
SoccerTwos/SoccerTwos-199499942.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5b35b2c1deebde9320815051f48750a5ce9d6fd998d1604f2f4ea1214487a6
3
+ size 28422481
SoccerTwos/SoccerTwos-199999836.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd0a08f220dbab7f00c9dc94fb410af805f095930a25ce2309e205bedb506d9
3
+ size 1764633
SoccerTwos/SoccerTwos-199999836.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2f5904efde17926119226f6fbc0f63fe4c97849a3c0e99eba1775607f40ca0
3
+ size 28422481
SoccerTwos/SoccerTwos-200000490.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd0a08f220dbab7f00c9dc94fb410af805f095930a25ce2309e205bedb506d9
3
+ size 1764633
SoccerTwos/SoccerTwos-200000490.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bc04437ae48c57ad17990b79d0477be6d03aca79994811bf9ff6c3c2ca2c6e1
3
+ size 28422481
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f57e02db6d1f664cd95663023ff409dc2f6d601ecb95d8f05ffd409a6ade617
3
  size 28422481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bc04437ae48c57ad17990b79d0477be6d03aca79994811bf9ff6c3c2ca2c6e1
3
  size 28422481
SoccerTwos/events.out.tfevents.1687874269.tensorado.174517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0421633be07744e3cd86a3765a57085d4a4a9121007bdc7fca0bf27e0f7ae52f
3
+ size 25695940
SoccerTwos/events.out.tfevents.1687925091.tensorado.230230.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dadcfddc4de2bcfec7d97c746d33ad252e7778380ce54c3ad11d71e5ec42f6
3
+ size 51390638
SoccerTwos/events.out.tfevents.1688012069.tensorado.344496.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0df311224e8b7752056c7d693b283fea70270f86af96c23c74afcc8563a11a
3
+ size 51390638
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 75000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 80000, "team_change": 320000, "swap_steps": 2000, "window": 20, "play_against_latest_model_ratio": 0.7, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 200000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -3,9 +3,9 @@ behaviors:
3
  SoccerTwos:
4
  trainer_type: poca
5
  hyperparameters:
6
- batch_size: 1024
7
  buffer_size: 20480
8
- learning_rate: 0.0002
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -37,16 +37,16 @@ behaviors:
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 75000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
44
  self_play:
45
- save_steps: 80000
46
- team_change: 320000
47
  swap_steps: 2000
48
- window: 20
49
- play_against_latest_model_ratio: 0.7
50
  initial_elo: 1200.0
51
  behavioral_cloning: null
52
  env_settings:
 
3
  SoccerTwos:
4
  trainer_type: poca
5
  hyperparameters:
6
+ batch_size: 2048
7
  buffer_size: 20480
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
+ max_steps: 200000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
44
  self_play:
45
+ save_steps: 50000
46
+ team_change: 200000
47
  swap_steps: 2000
48
+ window: 10
49
+ play_against_latest_model_ratio: 0.5
50
  initial_elo: 1200.0
51
  behavioral_cloning: null
52
  env_settings:
run_logs/Player-0.log CHANGED
@@ -11,7 +11,7 @@ NullGfxDevice:
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
- - Completed reload, in 0.093 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -36,7 +36,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
- UnloadTime: 0.442097 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
@@ -45,7 +45,7 @@ Memory Statistics:
45
  [ALLOC_TEMP_TLS] TLS Allocator
46
  StackAllocators :
47
  [ALLOC_TEMP_MAIN]
48
- Peak usage frame count: [8.0 KB-16.0 KB]: 563975 frames, [2.0 MB-4.0 MB]: 1 frames
49
  Initial Block Size 4.0 MB
50
  Current Block Size 4.0 MB
51
  Peak Allocated Bytes 2.1 MB
@@ -178,7 +178,7 @@ Memory Statistics:
178
  [ALLOC_TEMP_Job.Worker 7]
179
  Initial Block Size 256.0 KB
180
  Current Block Size 256.0 KB
181
- Peak Allocated Bytes 0 B
182
  Overflow Count 0
183
  [ALLOC_TEMP_Job.Worker 1]
184
  Initial Block Size 256.0 KB
@@ -188,7 +188,7 @@ Memory Statistics:
188
  [ALLOC_TEMP_Job.Worker 2]
189
  Initial Block Size 256.0 KB
190
  Current Block Size 256.0 KB
191
- Peak Allocated Bytes 0.7 KB
192
  Overflow Count 0
193
  [ALLOC_TEMP_Background Job.Worker 3]
194
  Initial Block Size 32.0 KB
@@ -231,22 +231,22 @@ Memory Statistics:
231
  Peak Allocated Bytes 0 B
232
  Overflow Count 0
233
  [ALLOC_DEFAULT] Dual Thread Allocator
234
- Peak main deferred allocation count 3
235
  [ALLOC_BUCKET]
236
  Large Block size 4.0 MB
237
  Used Block count 1
238
  Peak Allocated bytes 1.0 MB
239
  [ALLOC_DEFAULT_MAIN]
240
- Peak usage frame count: [4.0 MB-8.0 MB]: 563976 frames
241
  Requested Block Size 16.0 MB
242
  Peak Block count 1
243
- Peak Allocated memory 5.0 MB
244
  Peak Large allocation bytes 0 B
245
  [ALLOC_DEFAULT_THREAD]
246
- Peak usage frame count: [16.0 MB-32.0 MB]: 563976 frames
247
  Requested Block Size 16.0 MB
248
  Peak Block count 1
249
- Peak Allocated memory 17.3 MB
250
  Peak Large allocation bytes 16.0 MB
251
  [ALLOC_TEMP_JOB_1_FRAME]
252
  Initial Block Size 2.0 MB
@@ -275,13 +275,13 @@ Memory Statistics:
275
  Used Block count 1
276
  Peak Allocated bytes 1.0 MB
277
  [ALLOC_GFX_MAIN]
278
- Peak usage frame count: [32.0 KB-64.0 KB]: 563975 frames, [64.0 KB-128.0 KB]: 1 frames
279
  Requested Block Size 16.0 MB
280
  Peak Block count 1
281
  Peak Allocated memory 65.6 KB
282
  Peak Large allocation bytes 0 B
283
  [ALLOC_GFX_THREAD]
284
- Peak usage frame count: [128.0 KB-256.0 KB]: 563976 frames
285
  Requested Block Size 16.0 MB
286
  Peak Block count 1
287
  Peak Allocated memory 173.5 KB
@@ -293,13 +293,13 @@ Memory Statistics:
293
  Used Block count 1
294
  Peak Allocated bytes 1.0 MB
295
  [ALLOC_CACHEOBJECTS_MAIN]
296
- Peak usage frame count: [0.5 MB-1.0 MB]: 563976 frames
297
  Requested Block Size 4.0 MB
298
  Peak Block count 1
299
  Peak Allocated memory 0.6 MB
300
  Peak Large allocation bytes 0 B
301
  [ALLOC_CACHEOBJECTS_THREAD]
302
- Peak usage frame count: [0.5 MB-1.0 MB]: 563975 frames, [4.0 MB-8.0 MB]: 1 frames
303
  Requested Block Size 4.0 MB
304
  Peak Block count 2
305
  Peak Allocated memory 4.5 MB
@@ -311,13 +311,13 @@ Memory Statistics:
311
  Used Block count 1
312
  Peak Allocated bytes 1.0 MB
313
  [ALLOC_TYPETREE_MAIN]
314
- Peak usage frame count: [0-1.0 KB]: 563976 frames
315
  Requested Block Size 2.0 MB
316
  Peak Block count 1
317
  Peak Allocated memory 1.0 KB
318
  Peak Large allocation bytes 0 B
319
  [ALLOC_TYPETREE_THREAD]
320
- Peak usage frame count: [1.0 KB-2.0 KB]: 563975 frames, [2.0 KB-4.0 KB]: 1 frames
321
  Requested Block Size 2.0 MB
322
  Peak Block count 1
323
  Peak Allocated memory 2.2 KB
 
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.084 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
36
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
37
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
38
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
39
+ UnloadTime: 0.496726 ms
40
  Registered Communicator in Agent.
41
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
42
  requesting resize 84 x 84
 
45
  [ALLOC_TEMP_TLS] TLS Allocator
46
  StackAllocators :
47
  [ALLOC_TEMP_MAIN]
48
+ Peak usage frame count: [8.0 KB-16.0 KB]: 941705 frames, [2.0 MB-4.0 MB]: 1 frames
49
  Initial Block Size 4.0 MB
50
  Current Block Size 4.0 MB
51
  Peak Allocated Bytes 2.1 MB
 
178
  [ALLOC_TEMP_Job.Worker 7]
179
  Initial Block Size 256.0 KB
180
  Current Block Size 256.0 KB
181
+ Peak Allocated Bytes 0.7 KB
182
  Overflow Count 0
183
  [ALLOC_TEMP_Job.Worker 1]
184
  Initial Block Size 256.0 KB
 
188
  [ALLOC_TEMP_Job.Worker 2]
189
  Initial Block Size 256.0 KB
190
  Current Block Size 256.0 KB
191
+ Peak Allocated Bytes 0 B
192
  Overflow Count 0
193
  [ALLOC_TEMP_Background Job.Worker 3]
194
  Initial Block Size 32.0 KB
 
231
  Peak Allocated Bytes 0 B
232
  Overflow Count 0
233
  [ALLOC_DEFAULT] Dual Thread Allocator
234
+ Peak main deferred allocation count 4
235
  [ALLOC_BUCKET]
236
  Large Block size 4.0 MB
237
  Used Block count 1
238
  Peak Allocated bytes 1.0 MB
239
  [ALLOC_DEFAULT_MAIN]
240
+ Peak usage frame count: [4.0 MB-8.0 MB]: 941706 frames
241
  Requested Block Size 16.0 MB
242
  Peak Block count 1
243
+ Peak Allocated memory 5.1 MB
244
  Peak Large allocation bytes 0 B
245
  [ALLOC_DEFAULT_THREAD]
246
+ Peak usage frame count: [16.0 MB-32.0 MB]: 941706 frames
247
  Requested Block Size 16.0 MB
248
  Peak Block count 1
249
+ Peak Allocated memory 17.2 MB
250
  Peak Large allocation bytes 16.0 MB
251
  [ALLOC_TEMP_JOB_1_FRAME]
252
  Initial Block Size 2.0 MB
 
275
  Used Block count 1
276
  Peak Allocated bytes 1.0 MB
277
  [ALLOC_GFX_MAIN]
278
+ Peak usage frame count: [32.0 KB-64.0 KB]: 941705 frames, [64.0 KB-128.0 KB]: 1 frames
279
  Requested Block Size 16.0 MB
280
  Peak Block count 1
281
  Peak Allocated memory 65.6 KB
282
  Peak Large allocation bytes 0 B
283
  [ALLOC_GFX_THREAD]
284
+ Peak usage frame count: [128.0 KB-256.0 KB]: 941706 frames
285
  Requested Block Size 16.0 MB
286
  Peak Block count 1
287
  Peak Allocated memory 173.5 KB
 
293
  Used Block count 1
294
  Peak Allocated bytes 1.0 MB
295
  [ALLOC_CACHEOBJECTS_MAIN]
296
+ Peak usage frame count: [0.5 MB-1.0 MB]: 941706 frames
297
  Requested Block Size 4.0 MB
298
  Peak Block count 1
299
  Peak Allocated memory 0.6 MB
300
  Peak Large allocation bytes 0 B
301
  [ALLOC_CACHEOBJECTS_THREAD]
302
+ Peak usage frame count: [0.5 MB-1.0 MB]: 941705 frames, [4.0 MB-8.0 MB]: 1 frames
303
  Requested Block Size 4.0 MB
304
  Peak Block count 2
305
  Peak Allocated memory 4.5 MB
 
311
  Used Block count 1
312
  Peak Allocated bytes 1.0 MB
313
  [ALLOC_TYPETREE_MAIN]
314
+ Peak usage frame count: [0-1.0 KB]: 941706 frames
315
  Requested Block Size 2.0 MB
316
  Peak Block count 1
317
  Peak Allocated memory 1.0 KB
318
  Peak Large allocation bytes 0 B
319
  [ALLOC_TYPETREE_THREAD]
320
+ Peak usage frame count: [1.0 KB-2.0 KB]: 941705 frames, [2.0 KB-4.0 KB]: 1 frames
321
  Requested Block Size 2.0 MB
322
  Peak Block count 1
323
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,201 +2,201 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 1.351102352142334,
6
- "min": 1.2139328718185425,
7
- "max": 1.499452829360962,
8
- "count": 3000
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 25595.283203125,
12
- "min": 21485.06640625,
13
- "max": 34610.15234375,
14
- "count": 3000
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 60.71604938271605,
18
- "min": 45.94230769230769,
19
- "max": 111.73333333333333,
20
- "count": 3000
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 19672.0,
24
- "min": 18000.0,
25
- "max": 21428.0,
26
- "count": 3000
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1855.648801593294,
30
- "min": 1779.9860694905215,
31
- "max": 1907.8788060697548,
32
- "count": 3000
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 300615.1058581136,
36
- "min": 162321.63367544868,
37
- "max": 389266.4377070303,
38
- "count": 3000
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 74999888.0,
42
- "min": 45009986.0,
43
- "max": 74999888.0,
44
- "count": 3000
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 74999888.0,
48
- "min": 45009986.0,
49
- "max": 74999888.0,
50
- "count": 3000
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.031544286757707596,
54
- "min": -0.13769720494747162,
55
- "max": 0.09871241450309753,
56
- "count": 3000
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 5.110174179077148,
60
- "min": -24.413280487060547,
61
- "max": 16.090124130249023,
62
- "count": 3000
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.033151060342788696,
66
- "min": -0.14032487571239471,
67
- "max": 0.09837527573108673,
68
- "count": 3000
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 5.370471954345703,
72
- "min": -24.76893424987793,
73
- "max": 16.03516960144043,
74
- "count": 3000
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 3000
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 3000
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": 0.09084197658079642,
90
- "min": -0.4387682115794807,
91
- "max": 0.44735384721022387,
92
- "count": 3000
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": 14.71640020608902,
96
- "min": -66.25399994850159,
97
- "max": 58.1560001373291,
98
- "count": 3000
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": 0.09084197658079642,
102
- "min": -0.4387682115794807,
103
- "max": 0.44735384721022387,
104
- "count": 3000
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": 14.71640020608902,
108
- "min": -66.25399994850159,
109
- "max": 58.1560001373291,
110
- "count": 3000
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 3000
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 3000
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.030788333749903054,
126
- "min": 0.01815977915781938,
127
- "max": 0.03388751263167554,
128
- "count": 1455
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.030788333749903054,
132
- "min": 0.01815977915781938,
133
- "max": 0.03388751263167554,
134
- "count": 1455
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.09971378160019716,
138
- "min": 0.06663354604194562,
139
- "max": 0.1166419933239619,
140
- "count": 1455
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.09971378160019716,
144
- "min": 0.06663354604194562,
145
- "max": 0.1166419933239619,
146
- "count": 1455
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.10078321446975072,
150
- "min": 0.0676816205183665,
151
- "max": 0.11834517084062099,
152
- "count": 1455
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.10078321446975072,
156
- "min": 0.0676816205183665,
157
- "max": 0.11834517084062099,
158
- "count": 1455
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 0.00020000000000000006,
162
- "min": 0.00020000000000000006,
163
- "max": 0.0002000000000000001,
164
- "count": 1455
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 0.00020000000000000006,
168
- "min": 0.00020000000000000006,
169
- "max": 0.0002000000000000001,
170
- "count": 1455
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
- "value": 0.19999999999999993,
174
- "min": 0.1999999999999999,
175
- "max": 0.19999999999999993,
176
- "count": 1455
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
- "value": 0.19999999999999993,
180
- "min": 0.1999999999999999,
181
- "max": 0.19999999999999993,
182
- "count": 1455
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
- "count": 1455
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
- "count": 1455
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1687836667",
200
  "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]",
201
  "command_line_arguments": "/home/yoav/anaconda3/envs/2vs2_soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
202
  "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
- "end_time_seconds": "1687871338"
208
  },
209
- "total": 34671.135572214,
210
  "count": 1,
211
- "self": 0.2185233459895244,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.007574390998343006,
215
  "count": 1,
216
- "self": 0.007574390998343006
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 34670.90947447701,
220
  "count": 1,
221
- "self": 35.13137519544398,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 3.7628834190254565,
225
- "count": 95,
226
- "self": 3.7628834190254565
227
  },
228
  "TrainerController.advance": {
229
- "total": 34631.831811170545,
230
- "count": 2054685,
231
- "self": 32.93351431978226,
232
  "children": {
233
  "env_step": {
234
- "total": 24489.234598467243,
235
- "count": 2054685,
236
- "self": 17873.276705384036,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 6596.60783050218,
240
- "count": 2054685,
241
- "self": 179.0518261819525,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 6417.556004320228,
245
- "count": 3759876,
246
- "self": 6417.556004320228
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 19.350062581026577,
252
- "count": 2054685,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 34630.05029885686,
257
- "count": 2054685,
258
  "is_parallel": true,
259
- "self": 20141.767822244874,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
@@ -265,48 +265,48 @@
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
- "total": 0.0018154209974454716,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.0004750539519591257,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.0013403670454863459,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.0013403670454863459
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.016947556010563858,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.00039608500082977116,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.0003274079936090857,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.0003274079936090857
292
  },
293
  "communicator.exchange": {
294
- "total": 0.014955193008063361,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.014955193008063361
298
  },
299
  "steps_from_proto": {
300
- "total": 0.00126887000806164,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.00028444700001273304,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.000984423008048907,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.000984423008048907
310
  }
311
  }
312
  }
@@ -315,48 +315,48 @@
315
  }
316
  },
317
  "steps_from_proto": {
318
- "total": 0.13576419482706115,
319
- "count": 188,
320
  "is_parallel": true,
321
- "self": 0.02914394067192916,
322
  "children": {
323
  "_process_rank_one_or_two_observation": {
324
- "total": 0.10662025415513199,
325
- "count": 752,
326
  "is_parallel": true,
327
- "self": 0.10662025415513199
328
  }
329
  }
330
  },
331
  "UnityEnvironment.step": {
332
- "total": 14488.146712417161,
333
- "count": 2054684,
334
  "is_parallel": true,
335
- "self": 792.6817116667371,
336
  "children": {
337
  "UnityEnvironment._generate_step_input": {
338
- "total": 560.2664510110044,
339
- "count": 2054684,
340
  "is_parallel": true,
341
- "self": 560.2664510110044
342
  },
343
  "communicator.exchange": {
344
- "total": 10641.413183214609,
345
- "count": 2054684,
346
  "is_parallel": true,
347
- "self": 10641.413183214609
348
  },
349
  "steps_from_proto": {
350
- "total": 2493.7853665248113,
351
- "count": 4109368,
352
  "is_parallel": true,
353
- "self": 538.5585166657111,
354
  "children": {
355
  "_process_rank_one_or_two_observation": {
356
- "total": 1955.2268498591002,
357
- "count": 16437472,
358
  "is_parallel": true,
359
- "self": 1955.2268498591002
360
  }
361
  }
362
  }
@@ -369,31 +369,31 @@
369
  }
370
  },
371
  "trainer_advance": {
372
- "total": 10109.66369838352,
373
- "count": 2054685,
374
- "self": 210.14013616283773,
375
  "children": {
376
  "process_trajectory": {
377
- "total": 3666.5174054797244,
378
- "count": 2054685,
379
- "self": 3656.022602564786,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
- "total": 10.494802914938191,
383
- "count": 60,
384
- "self": 10.494802914938191
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
- "total": 6233.0061567409575,
390
- "count": 1455,
391
- "self": 3526.087065976375,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
- "total": 2706.9190907645825,
395
- "count": 87303,
396
- "self": 2706.9190907645825
397
  }
398
  }
399
  }
@@ -402,19 +402,19 @@
402
  }
403
  },
404
  "trainer_threads": {
405
- "total": 7.170019671320915e-07,
406
  "count": 1,
407
- "self": 7.170019671320915e-07
408
  },
409
  "TrainerController._save_models": {
410
- "total": 0.18340397499559913,
411
  "count": 1,
412
- "self": 0.0012349960015853867,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
- "total": 0.18216897899401374,
416
  "count": 1,
417
- "self": 0.18216897899401374
418
  }
419
  }
420
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.1379538774490356,
6
+ "min": 0.9347377419471741,
7
+ "max": 1.2154386043548584,
8
+ "count": 5000
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 22759.078125,
12
+ "min": 16144.0087890625,
13
+ "max": 28788.599609375,
14
+ "count": 5000
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 77.0,
18
+ "min": 47.0,
19
+ "max": 109.45652173913044,
20
+ "count": 5000
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 20328.0,
24
+ "min": 17524.0,
25
+ "max": 22004.0,
26
+ "count": 5000
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1796.1838299057483,
30
+ "min": 1766.9128790251336,
31
+ "max": 2009.782144467024,
32
+ "count": 5000
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 237096.26554755878,
36
+ "min": 162464.24892216737,
37
+ "max": 408058.2623436854,
38
+ "count": 5000
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 199999836.0,
42
+ "min": 150009962.0,
43
+ "max": 199999836.0,
44
+ "count": 5000
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 199999836.0,
48
+ "min": 150009962.0,
49
+ "max": 199999836.0,
50
+ "count": 5000
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.006698582321405411,
54
+ "min": -0.13151130080223083,
55
+ "max": 0.11459764093160629,
56
+ "count": 5000
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.884212851524353,
60
+ "min": -20.03160285949707,
61
+ "max": 15.929072380065918,
62
+ "count": 5000
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.008320164866745472,
66
+ "min": -0.13271933794021606,
67
+ "max": 0.1126069650053978,
68
+ "count": 5000
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 1.0982617139816284,
72
+ "min": -19.85004234313965,
73
+ "max": 15.652368545532227,
74
+ "count": 5000
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 5000
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 5000
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.09068181839856235,
90
+ "min": -0.4092910343203051,
91
+ "max": 0.3747726631679123,
92
+ "count": 5000
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -11.97000002861023,
96
+ "min": -65.99200028181076,
97
+ "max": 55.140800297260284,
98
+ "count": 5000
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.09068181839856235,
102
+ "min": -0.4092910343203051,
103
+ "max": 0.3747726631679123,
104
+ "count": 5000
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -11.97000002861023,
108
+ "min": -65.99200028181076,
109
+ "max": 55.140800297260284,
110
+ "count": 5000
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 5000
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 5000
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.01593884900600339,
126
+ "min": 0.01253225206813416,
127
+ "max": 0.026699458491930273,
128
+ "count": 2426
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01593884900600339,
132
+ "min": 0.01253225206813416,
133
+ "max": 0.026699458491930273,
134
+ "count": 2426
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.0718688689172268,
138
+ "min": 0.05997977815568447,
139
+ "max": 0.11612731764713922,
140
+ "count": 2426
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.0718688689172268,
144
+ "min": 0.05997977815568447,
145
+ "max": 0.11612731764713922,
146
+ "count": 2426
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.07221189687649408,
150
+ "min": 0.06059066231052081,
151
+ "max": 0.11714418778816858,
152
+ "count": 2426
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.07221189687649408,
156
+ "min": 0.06059066231052081,
157
+ "max": 0.11714418778816858,
158
+ "count": 2426
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2426
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2426
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 2426
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 2426
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
  "value": 0.005000000000000001,
186
  "min": 0.005000000000000001,
187
  "max": 0.005000000000000001,
188
+ "count": 2426
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
  "value": 0.005000000000000001,
192
  "min": 0.005000000000000001,
193
  "max": 0.005000000000000001,
194
+ "count": 2426
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1688012068",
200
  "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]",
201
  "command_line_arguments": "/home/yoav/anaconda3/envs/2vs2_soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
202
  "mlagents_version": "0.31.0.dev0",
 
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "1.11.0+cu102",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1688083976"
208
  },
209
+ "total": 71907.872196146,
210
  "count": 1,
211
+ "self": 0.21947479801019654,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.008186355989892036,
215
  "count": 1,
216
+ "self": 0.008186355989892036
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 71907.644534992,
220
  "count": 1,
221
+ "self": 71.42090288587497,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 7.242712540260982,
225
+ "count": 251,
226
+ "self": 7.242712540260982
227
  },
228
  "TrainerController.advance": {
229
+ "total": 71828.76494877986,
230
+ "count": 3422862,
231
+ "self": 66.44977636545082,
232
  "children": {
233
  "env_step": {
234
+ "total": 51541.429678388406,
235
+ "count": 3422862,
236
+ "self": 37821.549245519214,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 13680.694317420828,
240
+ "count": 3422862,
241
+ "self": 372.45103261907934,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 13308.243284801749,
245
+ "count": 6278128,
246
+ "self": 13308.243284801749
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 39.186115448363125,
252
+ "count": 3422862,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 71820.2092914654,
257
+ "count": 3422862,
258
  "is_parallel": true,
259
+ "self": 41044.5662780235,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0017572160286363214,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.00041944000986404717,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0013377760187722743,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.0013377760187722743
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.024257199984276667,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0006558480090461671,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00032233400270342827,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.00032233400270342827
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.02124975499464199,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.02124975499464199
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.0020292629778850824,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0004114069161005318,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.0016178560617845505,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.0016178560617845505
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "steps_from_proto": {
318
+ "total": 0.4603567080339417,
319
+ "count": 500,
320
  "is_parallel": true,
321
+ "self": 0.09795306270825677,
322
  "children": {
323
  "_process_rank_one_or_two_observation": {
324
+ "total": 0.3624036453256849,
325
+ "count": 2000,
326
  "is_parallel": true,
327
+ "self": 0.3624036453256849
328
  }
329
  }
330
  },
331
  "UnityEnvironment.step": {
332
+ "total": 30775.182656733872,
333
+ "count": 3422861,
334
  "is_parallel": true,
335
+ "self": 1669.3998983051279,
336
  "children": {
337
  "UnityEnvironment._generate_step_input": {
338
+ "total": 1166.5835989805928,
339
+ "count": 3422861,
340
  "is_parallel": true,
341
+ "self": 1166.5835989805928
342
  },
343
  "communicator.exchange": {
344
+ "total": 22646.438464231906,
345
+ "count": 3422861,
346
  "is_parallel": true,
347
+ "self": 22646.438464231906
348
  },
349
  "steps_from_proto": {
350
+ "total": 5292.760695216246,
351
+ "count": 6845722,
352
  "is_parallel": true,
353
+ "self": 1138.2786801359034,
354
  "children": {
355
  "_process_rank_one_or_two_observation": {
356
+ "total": 4154.4820150803425,
357
+ "count": 27382888,
358
  "is_parallel": true,
359
+ "self": 4154.4820150803425
360
  }
361
  }
362
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 20220.885494026006,
373
+ "count": 3422862,
374
+ "self": 427.4996939775883,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 7681.809909527277,
378
+ "count": 3422862,
379
+ "self": 7659.8104141058575,
380
  "children": {
381
  "RLTrainer._checkpoint": {
382
+ "total": 21.99949542141985,
383
+ "count": 100,
384
+ "self": 21.99949542141985
385
  }
386
  }
387
  },
388
  "_update_policy": {
389
+ "total": 12111.57589052114,
390
+ "count": 2426,
391
+ "self": 7725.115777124796,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 4386.460113396344,
395
+ "count": 72780,
396
+ "self": 4386.460113396344
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 1.167994923889637e-06,
406
  "count": 1,
407
+ "self": 1.167994923889637e-06
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.21596961800241843,
411
  "count": 1,
412
+ "self": 0.0015275460318662226,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.2144420719705522,
416
  "count": 1,
417
+ "self": 0.2144420719705522
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -2,59 +2,59 @@
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
- "steps": 73499956,
6
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-73499956.onnx",
7
  "reward": 0.0,
8
- "creation_time": 1687869574.2571676,
9
  "auxillary_file_paths": [
10
- "results/SoccerTwos/SoccerTwos/SoccerTwos-73499956.pt"
11
  ]
12
  },
13
  {
14
- "steps": 73999940,
15
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-73999940.onnx",
16
  "reward": 0.0,
17
- "creation_time": 1687870158.123428,
18
  "auxillary_file_paths": [
19
- "results/SoccerTwos/SoccerTwos/SoccerTwos-73999940.pt"
20
  ]
21
  },
22
  {
23
- "steps": 74499976,
24
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-74499976.onnx",
25
  "reward": 0.0,
26
- "creation_time": 1687870750.5032022,
27
  "auxillary_file_paths": [
28
- "results/SoccerTwos/SoccerTwos/SoccerTwos-74499976.pt"
29
  ]
30
  },
31
  {
32
- "steps": 74999888,
33
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-74999888.onnx",
34
  "reward": 0.0,
35
- "creation_time": 1687871338.2930057,
36
  "auxillary_file_paths": [
37
- "results/SoccerTwos/SoccerTwos/SoccerTwos-74999888.pt"
38
  ]
39
  },
40
  {
41
- "steps": 75000050,
42
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-75000050.onnx",
43
  "reward": 0.0,
44
- "creation_time": 1687871338.487278,
45
  "auxillary_file_paths": [
46
- "results/SoccerTwos/SoccerTwos/SoccerTwos-75000050.pt"
47
  ]
48
  }
49
  ],
50
- "elo": 1857.2024356089075,
51
  "final_checkpoint": {
52
- "steps": 75000050,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
- "creation_time": 1687871338.487278,
56
  "auxillary_file_paths": [
57
- "results/SoccerTwos/SoccerTwos/SoccerTwos-75000050.pt"
58
  ]
59
  }
60
  },
 
2
  "SoccerTwos": {
3
  "checkpoints": [
4
  {
5
+ "steps": 198499942,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-198499942.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1688081682.895257,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-198499942.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 198999874,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-198999874.onnx",
16
  "reward": 0.0,
17
+ "creation_time": 1688082452.258048,
18
  "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-198999874.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 199499942,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-199499942.onnx",
25
  "reward": 0.0,
26
+ "creation_time": 1688083217.684971,
27
  "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-199499942.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 199999836,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-199999836.onnx",
34
  "reward": 0.0,
35
+ "creation_time": 1688083975.8580647,
36
  "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-199999836.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200000490,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-200000490.onnx",
43
  "reward": 0.0,
44
+ "creation_time": 1688083976.1915483,
45
  "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-200000490.pt"
47
  ]
48
  }
49
  ],
50
+ "elo": 1797.3182988814417,
51
  "final_checkpoint": {
52
+ "steps": 200000490,
53
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
  "reward": 0.0,
55
+ "creation_time": 1688083976.1915483,
56
  "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-200000490.pt"
58
  ]
59
  }
60
  },