Hugging Face's logo

guocheng66
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
guocheng66 commited on
Commit
8a152f0
•
1 Parent(s): 19e81c6

Second Push

Browse files
Files changed (14) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-1001494.onnx +3 -0
  3. SoccerTwos/SoccerTwos-1001494.pt +3 -0
  4. SoccerTwos/SoccerTwos-499090.onnx +3 -0
  5. SoccerTwos/SoccerTwos-499090.pt +3 -0
  6. SoccerTwos/SoccerTwos-999684.onnx +3 -0
  7. SoccerTwos/SoccerTwos-999684.pt +3 -0
  8. SoccerTwos/checkpoint.pt +2 -2
  9. SoccerTwos/events.out.tfevents.1697686349.7a15edb6275d.2024.0 +3 -0
  10. config.json +1 -1
  11. configuration.yaml +3 -3
  12. run_logs/Player-0.log +355 -19
  13. run_logs/timers.json +205 -184
  14. run_logs/training_status.json +26 -8
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22118ebad8dadccf2adae452ec4f6ded2cbaf9a32646efec321e828e4eba0dc2
3
  size 1768746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84ba2bcfb345951a285a700f19a7becbbad447542ce9fcc490fd01ba1acc82a
3
  size 1768746
SoccerTwos/SoccerTwos-1001494.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84ba2bcfb345951a285a700f19a7becbbad447542ce9fcc490fd01ba1acc82a
3
+ size 1768746
SoccerTwos/SoccerTwos-1001494.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60dfbb5ed5abc693e9499eb23acb3c1d354bf810b809733d7e14af0da7819686
3
+ size 28431567
SoccerTwos/SoccerTwos-499090.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198dd5007e32ddb62507325cb2877bba9e04633084af94425c869c24c5278d6b
3
+ size 1768746
SoccerTwos/SoccerTwos-499090.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4a01d3b2b2ada26c712b3d432327405b8bf6de6efa64ac2b1756fe205cf5fd
3
+ size 28431445
SoccerTwos/SoccerTwos-999684.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84ba2bcfb345951a285a700f19a7becbbad447542ce9fcc490fd01ba1acc82a
3
+ size 1768746
SoccerTwos/SoccerTwos-999684.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b6edb27747cb0ccec1d4981f82e640ee3dec70a14c46b38e7818289862b73a
3
+ size 28431445
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34abd56a345b7d46cafd2b6999763094fdb771dfb3bfb85d5c6cc7e4da29d3ff
3
- size 28428927
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76341c8c15c11e7eb0d0827766c5fac4affc856cfd6b53abc55d7c7ee65dfb4
3
+ size 28430591
SoccerTwos/events.out.tfevents.1697686349.7a15edb6275d.2024.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824313605fcd611b58e43aca4a86da53eae9f723134f0e1e273b0aa7d620d985
3
+ size 729209
config.json CHANGED
@@ -1 +1 @@
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": 50000000, "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.x86_64", "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 4096, "buffer_size": 20480, "learning_rate": 0.0006, "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": 1000000, "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.x86_64", "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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 CHANGED
@@ -3,9 +3,9 @@ behaviors:
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
@@ -37,7 +37,7 @@ behaviors:
37
  init_path: null
38
  keep_checkpoints: 5
39
  even_checkpoints: false
40
- max_steps: 50000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
 
3
  SoccerTwos:
4
  trainer_type: poca
5
  hyperparameters:
6
+ batch_size: 4096
7
  buffer_size: 20480
8
+ learning_rate: 0.0006
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: 1000000
41
  time_horizon: 1000
42
  summary_freq: 10000
43
  threaded: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/Man
2
  Mono config path = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.149 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -59,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
59
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
60
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
61
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
62
- UnloadTime: 0.970030 ms
63
  Registered Communicator in Agent.
64
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
65
  requesting resize 84 x 84
@@ -129,12 +126,351 @@ TOO LONG
129
  TOO LONG
130
  TOO LONG
131
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
132
  Setting up 1 worker threads for Enlighten.
133
  Memory Statistics:
134
  [ALLOC_TEMP_TLS] TLS Allocator
135
  StackAllocators :
136
  [ALLOC_TEMP_MAIN]
137
- Peak usage frame count: [8.0 KB-16.0 KB]: 3246 frames, [2.0 MB-4.0 MB]: 1 frames
138
  Initial Block Size 4.0 MB
139
  Current Block Size 4.0 MB
140
  Peak Allocated Bytes 2.1 MB
@@ -162,7 +498,7 @@ Memory Statistics:
162
  [ALLOC_TEMP_Job.Worker 0]
163
  Initial Block Size 256.0 KB
164
  Current Block Size 256.0 KB
165
- Peak Allocated Bytes 0 B
166
  Overflow Count 0
167
  [ALLOC_TEMP_Background Job.Worker 10]
168
  Initial Block Size 32.0 KB
@@ -250,19 +586,19 @@ Memory Statistics:
250
  Peak Allocated Bytes 0 B
251
  Overflow Count 0
252
  [ALLOC_DEFAULT] Dual Thread Allocator
253
- Peak main deferred allocation count 3
254
  [ALLOC_BUCKET]
255
  Large Block size 4.0 MB
256
  Used Block count 1
257
  Peak Allocated bytes 1.0 MB
258
  [ALLOC_DEFAULT_MAIN]
259
- Peak usage frame count: [4.0 MB-8.0 MB]: 3247 frames
260
  Requested Block Size 16.0 MB
261
  Peak Block count 1
262
- Peak Allocated memory 4.6 MB
263
  Peak Large allocation bytes 0 B
264
  [ALLOC_DEFAULT_THREAD]
265
- Peak usage frame count: [16.0 MB-32.0 MB]: 3247 frames
266
  Requested Block Size 16.0 MB
267
  Peak Block count 1
268
  Peak Allocated memory 17.6 MB
@@ -294,13 +630,13 @@ Memory Statistics:
294
  Used Block count 1
295
  Peak Allocated bytes 1.0 MB
296
  [ALLOC_GFX_MAIN]
297
- Peak usage frame count: [32.0 KB-64.0 KB]: 3246 frames, [64.0 KB-128.0 KB]: 1 frames
298
  Requested Block Size 16.0 MB
299
  Peak Block count 1
300
  Peak Allocated memory 65.6 KB
301
  Peak Large allocation bytes 0 B
302
  [ALLOC_GFX_THREAD]
303
- Peak usage frame count: [128.0 KB-256.0 KB]: 3247 frames
304
  Requested Block Size 16.0 MB
305
  Peak Block count 1
306
  Peak Allocated memory 173.5 KB
@@ -312,16 +648,16 @@ Memory Statistics:
312
  Used Block count 1
313
  Peak Allocated bytes 1.0 MB
314
  [ALLOC_CACHEOBJECTS_MAIN]
315
- Peak usage frame count: [0.5 MB-1.0 MB]: 3247 frames
316
  Requested Block Size 4.0 MB
317
  Peak Block count 1
318
  Peak Allocated memory 0.6 MB
319
  Peak Large allocation bytes 0 B
320
  [ALLOC_CACHEOBJECTS_THREAD]
321
- Peak usage frame count: [0.5 MB-1.0 MB]: 3246 frames, [4.0 MB-8.0 MB]: 1 frames
322
  Requested Block Size 4.0 MB
323
- Peak Block count 2
324
- Peak Allocated memory 4.1 MB
325
  Peak Large allocation bytes 0 B
326
  [ALLOC_TYPETREE] Dual Thread Allocator
327
  Peak main deferred allocation count 0
@@ -330,13 +666,13 @@ Memory Statistics:
330
  Used Block count 1
331
  Peak Allocated bytes 1.0 MB
332
  [ALLOC_TYPETREE_MAIN]
333
- Peak usage frame count: [0-1.0 KB]: 3247 frames
334
  Requested Block Size 2.0 MB
335
  Peak Block count 1
336
  Peak Allocated memory 1.0 KB
337
  Peak Large allocation bytes 0 B
338
  [ALLOC_TYPETREE_THREAD]
339
- Peak usage frame count: [1.0 KB-2.0 KB]: 3246 frames, [2.0 KB-4.0 KB]: 1 frames
340
  Requested Block Size 2.0 MB
341
  Peak Block count 1
342
  Peak Allocated memory 2.2 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.122 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
56
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
57
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
58
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
59
+ UnloadTime: 0.798787 ms
60
  Registered Communicator in Agent.
61
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
62
  requesting resize 84 x 84
 
126
  TOO LONG
127
  TOO LONG
128
  TOO LONG
129
+ TOO LONG
130
+ TOO LONG
131
+ TOO LONG
132
+ TOO LONG
133
+ TOO LONG
134
+ TOO LONG
135
+ TOO LONG
136
+ TOO LONG
137
+ TOO LONG
138
+ TOO LONG
139
+ TOO LONG
140
+ TOO LONG
141
+ TOO LONG
142
+ TOO LONG
143
+ TOO LONG
144
+ TOO LONG
145
+ TOO LONG
146
+ TOO LONG
147
+ TOO LONG
148
+ TOO LONG
149
+ TOO LONG
150
+ TOO LONG
151
+ TOO LONG
152
+ TOO LONG
153
+ TOO LONG
154
+ TOO LONG
155
+ TOO LONG
156
+ TOO LONG
157
+ TOO LONG
158
+ TOO LONG
159
+ TOO LONG
160
+ TOO LONG
161
+ TOO LONG
162
+ TOO LONG
163
+ TOO LONG
164
+ TOO LONG
165
+ TOO LONG
166
+ TOO LONG
167
+ TOO LONG
168
+ TOO LONG
169
+ TOO LONG
170
+ TOO LONG
171
+ TOO LONG
172
+ TOO LONG
173
+ TOO LONG
174
+ TOO LONG
175
+ TOO LONG
176
+ TOO LONG
177
+ TOO LONG
178
+ TOO LONG
179
+ TOO LONG
180
+ TOO LONG
181
+ TOO LONG
182
+ TOO LONG
183
+ TOO LONG
184
+ TOO LONG
185
+ TOO LONG
186
+ TOO LONG
187
+ TOO LONG
188
+ TOO LONG
189
+ TOO LONG
190
+ TOO LONG
191
+ TOO LONG
192
+ TOO LONG
193
+ TOO LONG
194
+ TOO LONG
195
+ TOO LONG
196
+ TOO LONG
197
+ TOO LONG
198
+ TOO LONG
199
+ TOO LONG
200
+ TOO LONG
201
+ TOO LONG
202
+ TOO LONG
203
+ TOO LONG
204
+ TOO LONG
205
+ TOO LONG
206
+ TOO LONG
207
+ TOO LONG
208
+ TOO LONG
209
+ TOO LONG
210
+ TOO LONG
211
+ TOO LONG
212
+ TOO LONG
213
+ TOO LONG
214
+ TOO LONG
215
+ TOO LONG
216
+ TOO LONG
217
+ TOO LONG
218
+ TOO LONG
219
+ TOO LONG
220
+ TOO LONG
221
+ TOO LONG
222
+ TOO LONG
223
+ TOO LONG
224
+ TOO LONG
225
+ TOO LONG
226
+ TOO LONG
227
+ TOO LONG
228
+ TOO LONG
229
+ TOO LONG
230
+ TOO LONG
231
+ TOO LONG
232
+ TOO LONG
233
+ TOO LONG
234
+ TOO LONG
235
+ TOO LONG
236
+ TOO LONG
237
+ TOO LONG
238
+ TOO LONG
239
+ TOO LONG
240
+ TOO LONG
241
+ TOO LONG
242
+ TOO LONG
243
+ TOO LONG
244
+ TOO LONG
245
+ TOO LONG
246
+ TOO LONG
247
+ TOO LONG
248
+ TOO LONG
249
+ TOO LONG
250
+ TOO LONG
251
+ TOO LONG
252
+ TOO LONG
253
+ TOO LONG
254
+ TOO LONG
255
+ TOO LONG
256
+ TOO LONG
257
+ TOO LONG
258
+ TOO LONG
259
+ TOO LONG
260
+ TOO LONG
261
+ TOO LONG
262
+ TOO LONG
263
+ TOO LONG
264
+ TOO LONG
265
+ TOO LONG
266
+ TOO LONG
267
+ TOO LONG
268
+ TOO LONG
269
+ TOO LONG
270
+ TOO LONG
271
+ TOO LONG
272
+ TOO LONG
273
+ TOO LONG
274
+ TOO LONG
275
+ TOO LONG
276
+ TOO LONG
277
+ TOO LONG
278
+ TOO LONG
279
+ TOO LONG
280
+ TOO LONG
281
+ TOO LONG
282
+ TOO LONG
283
+ TOO LONG
284
+ TOO LONG
285
+ TOO LONG
286
+ TOO LONG
287
+ TOO LONG
288
+ TOO LONG
289
+ TOO LONG
290
+ TOO LONG
291
+ TOO LONG
292
+ TOO LONG
293
+ TOO LONG
294
+ TOO LONG
295
+ TOO LONG
296
+ TOO LONG
297
+ TOO LONG
298
+ TOO LONG
299
+ TOO LONG
300
+ TOO LONG
301
+ TOO LONG
302
+ TOO LONG
303
+ TOO LONG
304
+ TOO LONG
305
+ TOO LONG
306
+ TOO LONG
307
+ TOO LONG
308
+ TOO LONG
309
+ TOO LONG
310
+ TOO LONG
311
+ TOO LONG
312
+ TOO LONG
313
+ TOO LONG
314
+ TOO LONG
315
+ TOO LONG
316
+ TOO LONG
317
+ TOO LONG
318
+ TOO LONG
319
+ TOO LONG
320
+ TOO LONG
321
+ TOO LONG
322
+ TOO LONG
323
+ TOO LONG
324
+ TOO LONG
325
+ TOO LONG
326
+ TOO LONG
327
+ TOO LONG
328
+ TOO LONG
329
+ TOO LONG
330
+ TOO LONG
331
+ TOO LONG
332
+ TOO LONG
333
+ TOO LONG
334
+ TOO LONG
335
+ TOO LONG
336
+ TOO LONG
337
+ TOO LONG
338
+ TOO LONG
339
+ TOO LONG
340
+ TOO LONG
341
+ TOO LONG
342
+ TOO LONG
343
+ TOO LONG
344
+ TOO LONG
345
+ TOO LONG
346
+ TOO LONG
347
+ TOO LONG
348
+ TOO LONG
349
+ TOO LONG
350
+ TOO LONG
351
+ TOO LONG
352
+ TOO LONG
353
+ TOO LONG
354
+ TOO LONG
355
+ TOO LONG
356
+ TOO LONG
357
+ TOO LONG
358
+ TOO LONG
359
+ TOO LONG
360
+ TOO LONG
361
+ TOO LONG
362
+ TOO LONG
363
+ TOO LONG
364
+ TOO LONG
365
+ TOO LONG
366
+ TOO LONG
367
+ TOO LONG
368
+ TOO LONG
369
+ TOO LONG
370
+ TOO LONG
371
+ TOO LONG
372
+ TOO LONG
373
+ TOO LONG
374
+ TOO LONG
375
+ TOO LONG
376
+ TOO LONG
377
+ TOO LONG
378
+ TOO LONG
379
+ TOO LONG
380
+ TOO LONG
381
+ TOO LONG
382
+ TOO LONG
383
+ TOO LONG
384
+ TOO LONG
385
+ TOO LONG
386
+ TOO LONG
387
+ TOO LONG
388
+ TOO LONG
389
+ TOO LONG
390
+ TOO LONG
391
+ TOO LONG
392
+ TOO LONG
393
+ TOO LONG
394
+ TOO LONG
395
+ TOO LONG
396
+ TOO LONG
397
+ TOO LONG
398
+ TOO LONG
399
+ TOO LONG
400
+ TOO LONG
401
+ TOO LONG
402
+ TOO LONG
403
+ TOO LONG
404
+ TOO LONG
405
+ TOO LONG
406
+ TOO LONG
407
+ TOO LONG
408
+ TOO LONG
409
+ TOO LONG
410
+ TOO LONG
411
+ TOO LONG
412
+ TOO LONG
413
+ TOO LONG
414
+ TOO LONG
415
+ TOO LONG
416
+ TOO LONG
417
+ TOO LONG
418
+ TOO LONG
419
+ TOO LONG
420
+ TOO LONG
421
+ TOO LONG
422
+ TOO LONG
423
+ TOO LONG
424
+ TOO LONG
425
+ TOO LONG
426
+ TOO LONG
427
+ TOO LONG
428
+ TOO LONG
429
+ TOO LONG
430
+ TOO LONG
431
+ TOO LONG
432
+ TOO LONG
433
+ TOO LONG
434
+ TOO LONG
435
+ TOO LONG
436
+ TOO LONG
437
+ TOO LONG
438
+ TOO LONG
439
+ TOO LONG
440
+ TOO LONG
441
+ TOO LONG
442
+ TOO LONG
443
+ TOO LONG
444
+ TOO LONG
445
+ TOO LONG
446
+ TOO LONG
447
+ TOO LONG
448
+ TOO LONG
449
+ TOO LONG
450
+ TOO LONG
451
+ TOO LONG
452
+ TOO LONG
453
+ TOO LONG
454
+ TOO LONG
455
+ TOO LONG
456
+ TOO LONG
457
+ TOO LONG
458
+ TOO LONG
459
+ TOO LONG
460
+ TOO LONG
461
+ TOO LONG
462
+ TOO LONG
463
+ TOO LONG
464
+ TOO LONG
465
+ TOO LONG
466
+ TOO LONG
467
+ TOO LONG
468
  Setting up 1 worker threads for Enlighten.
469
  Memory Statistics:
470
  [ALLOC_TEMP_TLS] TLS Allocator
471
  StackAllocators :
472
  [ALLOC_TEMP_MAIN]
473
+ Peak usage frame count: [8.0 KB-16.0 KB]: 19376 frames, [2.0 MB-4.0 MB]: 1 frames
474
  Initial Block Size 4.0 MB
475
  Current Block Size 4.0 MB
476
  Peak Allocated Bytes 2.1 MB
 
498
  [ALLOC_TEMP_Job.Worker 0]
499
  Initial Block Size 256.0 KB
500
  Current Block Size 256.0 KB
501
+ Peak Allocated Bytes 0.7 KB
502
  Overflow Count 0
503
  [ALLOC_TEMP_Background Job.Worker 10]
504
  Initial Block Size 32.0 KB
 
586
  Peak Allocated Bytes 0 B
587
  Overflow Count 0
588
  [ALLOC_DEFAULT] Dual Thread Allocator
589
+ Peak main deferred allocation count 4
590
  [ALLOC_BUCKET]
591
  Large Block size 4.0 MB
592
  Used Block count 1
593
  Peak Allocated bytes 1.0 MB
594
  [ALLOC_DEFAULT_MAIN]
595
+ Peak usage frame count: [4.0 MB-8.0 MB]: 19377 frames
596
  Requested Block Size 16.0 MB
597
  Peak Block count 1
598
+ Peak Allocated memory 4.7 MB
599
  Peak Large allocation bytes 0 B
600
  [ALLOC_DEFAULT_THREAD]
601
+ Peak usage frame count: [16.0 MB-32.0 MB]: 19377 frames
602
  Requested Block Size 16.0 MB
603
  Peak Block count 1
604
  Peak Allocated memory 17.6 MB
 
630
  Used Block count 1
631
  Peak Allocated bytes 1.0 MB
632
  [ALLOC_GFX_MAIN]
633
+ Peak usage frame count: [32.0 KB-64.0 KB]: 19376 frames, [64.0 KB-128.0 KB]: 1 frames
634
  Requested Block Size 16.0 MB
635
  Peak Block count 1
636
  Peak Allocated memory 65.6 KB
637
  Peak Large allocation bytes 0 B
638
  [ALLOC_GFX_THREAD]
639
+ Peak usage frame count: [128.0 KB-256.0 KB]: 19377 frames
640
  Requested Block Size 16.0 MB
641
  Peak Block count 1
642
  Peak Allocated memory 173.5 KB
 
648
  Used Block count 1
649
  Peak Allocated bytes 1.0 MB
650
  [ALLOC_CACHEOBJECTS_MAIN]
651
+ Peak usage frame count: [0.5 MB-1.0 MB]: 19377 frames
652
  Requested Block Size 4.0 MB
653
  Peak Block count 1
654
  Peak Allocated memory 0.6 MB
655
  Peak Large allocation bytes 0 B
656
  [ALLOC_CACHEOBJECTS_THREAD]
657
+ Peak usage frame count: [0.5 MB-1.0 MB]: 19376 frames, [2.0 MB-4.0 MB]: 1 frames
658
  Requested Block Size 4.0 MB
659
+ Peak Block count 1
660
+ Peak Allocated memory 4.0 MB
661
  Peak Large allocation bytes 0 B
662
  [ALLOC_TYPETREE] Dual Thread Allocator
663
  Peak main deferred allocation count 0
 
666
  Used Block count 1
667
  Peak Allocated bytes 1.0 MB
668
  [ALLOC_TYPETREE_MAIN]
669
+ Peak usage frame count: [0-1.0 KB]: 19377 frames
670
  Requested Block Size 2.0 MB
671
  Peak Block count 1
672
  Peak Allocated memory 1.0 KB
673
  Peak Large allocation bytes 0 B
674
  [ALLOC_TYPETREE_THREAD]
675
+ Peak usage frame count: [1.0 KB-2.0 KB]: 19376 frames, [2.0 KB-4.0 KB]: 1 frames
676
  Requested Block Size 2.0 MB
677
  Peak Block count 1
678
  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": 3.2498252391815186,
6
- "min": 3.2498252391815186,
7
- "max": 3.2957494258880615,
8
- "count": 16
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 68012.34375,
12
- "min": 40204.31640625,
13
- "max": 105463.984375,
14
- "count": 16
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 831.4,
18
- "min": 644.5,
19
  "max": 999.0,
20
- "count": 16
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 16628.0,
24
- "min": 14772.0,
25
- "max": 26372.0,
26
- "count": 16
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1200.011282228457,
30
- "min": 1196.9986603914529,
31
- "max": 1201.6990760912279,
32
- "count": 11
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 4800.045128913828,
36
- "min": 2399.965563437694,
37
- "max": 12016.990760912278,
38
- "count": 11
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 159250.0,
42
- "min": 9202.0,
43
- "max": 159250.0,
44
- "count": 16
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 159250.0,
48
- "min": 9202.0,
49
- "max": 159250.0,
50
- "count": 16
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.008204853162169456,
54
- "min": 0.0027194288559257984,
55
- "max": 0.06095992028713226,
56
- "count": 16
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 0.09025338292121887,
60
- "min": 0.03535257652401924,
61
- "max": 0.7924005389213562,
62
- "count": 16
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.008218503557145596,
66
- "min": 0.0029141937848180532,
67
- "max": 0.06097675859928131,
68
- "count": 16
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 0.09040354192256927,
72
- "min": 0.03788451850414276,
73
- "max": 0.7926248908042908,
74
- "count": 16
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 16
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 16
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": -0.13785454630851746,
90
- "min": -0.36363636363636365,
91
- "max": 0.21687692403793335,
92
- "count": 16
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": -1.516400009393692,
96
- "min": -4.251600027084351,
97
- "max": 2.8194000124931335,
98
- "count": 16
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": -0.13785454630851746,
102
- "min": -0.36363636363636365,
103
- "max": 0.21687692403793335,
104
- "count": 16
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": -1.516400009393692,
108
- "min": -4.251600027084351,
109
- "max": 2.8194000124931335,
110
- "count": 16
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 16
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 16
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
- "value": 0.014225690786649163,
126
- "min": 0.014225690786649163,
127
- "max": 0.0217047512337255,
128
- "count": 7
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
- "value": 0.014225690786649163,
132
- "min": 0.014225690786649163,
133
- "max": 0.0217047512337255,
134
- "count": 7
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
- "value": 0.0009059652307769284,
138
- "min": 0.0008610313307144679,
139
- "max": 0.005003788516235849,
140
- "count": 7
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
- "value": 0.0009059652307769284,
144
- "min": 0.0008610313307144679,
145
- "max": 0.005003788516235849,
146
- "count": 7
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
- "value": 0.0009158240757339323,
150
- "min": 0.0008748267233992616,
151
- "max": 0.005044405449492236,
152
- "count": 7
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
- "value": 0.0009158240757339323,
156
- "min": 0.0008748267233992616,
157
- "max": 0.005044405449492236,
158
- "count": 7
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
- "value": 0.0003,
162
- "min": 0.0003,
163
- "max": 0.0003,
164
- "count": 7
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
- "value": 0.0003,
168
- "min": 0.0003,
169
- "max": 0.0003,
170
- "count": 7
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
- "count": 7
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
- "count": 7
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
- "value": 0.005000000000000001,
186
- "min": 0.005000000000000001,
187
- "max": 0.005000000000000001,
188
- "count": 7
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
- "value": 0.005000000000000001,
192
- "min": 0.005000000000000001,
193
- "max": 0.005000000000000001,
194
- "count": 7
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1697684702",
200
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
201
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
@@ -204,59 +204,59 @@
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.0.1+cu118",
206
  "numpy_version": "1.23.5",
207
- "end_time_seconds": "1697685594"
208
  },
209
- "total": 892.3789655999999,
210
  "count": 1,
211
- "self": 0.37092944300002273,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.07751938699993843,
215
  "count": 1,
216
- "self": 0.07751938699993843
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 891.9305167699999,
220
  "count": 1,
221
- "self": 0.3805751149968728,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 1.588794888999928,
225
- "count": 1,
226
- "self": 1.588794888999928
227
  },
228
  "TrainerController.advance": {
229
- "total": 889.4396380340033,
230
- "count": 10891,
231
- "self": 0.44354376202591084,
232
  "children": {
233
  "env_step": {
234
- "total": 369.67385742198667,
235
- "count": 10891,
236
- "self": 298.68240304696565,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 70.74381621701491,
240
- "count": 10891,
241
- "self": 3.0389947630369534,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 67.70482145397796,
245
- "count": 21642,
246
- "self": 67.70482145397796
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.24763815800611155,
252
- "count": 10890,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 890.1284948959899,
257
- "count": 10890,
258
  "is_parallel": true,
259
- "self": 642.1720417669906,
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": 0.009498120000216659,
269
  "count": 2,
270
  "is_parallel": true,
271
- "self": 0.005277394000358981,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
- "total": 0.004220725999857677,
275
  "count": 8,
276
  "is_parallel": true,
277
- "self": 0.004220725999857677
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
- "total": 0.07662100500010638,
283
  "count": 1,
284
  "is_parallel": true,
285
- "self": 0.0015879869999935181,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
- "total": 0.0014820999999756168,
289
  "count": 1,
290
  "is_parallel": true,
291
- "self": 0.0014820999999756168
292
  },
293
  "communicator.exchange": {
294
- "total": 0.06878995500005658,
295
  "count": 1,
296
  "is_parallel": true,
297
- "self": 0.06878995500005658
298
  },
299
  "steps_from_proto": {
300
- "total": 0.004760963000080665,
301
  "count": 2,
302
  "is_parallel": true,
303
- "self": 0.0007841609999559296,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
- "total": 0.003976802000124735,
307
  "count": 8,
308
  "is_parallel": true,
309
- "self": 0.003976802000124735
310
  }
311
  }
312
  }
@@ -315,38 +315,52 @@
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
- "total": 247.95645312899933,
319
- "count": 10889,
320
  "is_parallel": true,
321
- "self": 15.642344614018157,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
- "total": 9.171408972998279,
325
- "count": 10889,
326
  "is_parallel": true,
327
- "self": 9.171408972998279
328
  },
329
  "communicator.exchange": {
330
- "total": 175.8291073189905,
331
- "count": 10889,
332
  "is_parallel": true,
333
- "self": 175.8291073189905
334
  },
335
  "steps_from_proto": {
336
- "total": 47.31359222299238,
337
- "count": 21778,
338
  "is_parallel": true,
339
- "self": 8.092771005980012,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
- "total": 39.22082121701237,
343
- "count": 87112,
344
  "is_parallel": true,
345
- "self": 39.22082121701237
346
  }
347
  }
348
  }
349
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
350
  }
351
  }
352
  }
@@ -355,24 +369,31 @@
355
  }
356
  },
357
  "trainer_advance": {
358
- "total": 519.3222368499908,
359
- "count": 10890,
360
- "self": 3.5953262919724693,
361
  "children": {
362
  "process_trajectory": {
363
- "total": 69.1600442570184,
364
- "count": 10890,
365
- "self": 69.1600442570184
 
 
 
 
 
 
 
366
  },
367
  "_update_policy": {
368
- "total": 446.5668663009999,
369
- "count": 7,
370
- "self": 30.450832707001382,
371
  "children": {
372
  "TorchPOCAOptimizer.update": {
373
- "total": 416.1160335939985,
374
- "count": 210,
375
- "self": 416.1160335939985
376
  }
377
  }
378
  }
@@ -381,19 +402,19 @@
381
  }
382
  },
383
  "trainer_threads": {
384
- "total": 1.9579999843699625e-06,
385
  "count": 1,
386
- "self": 1.9579999843699625e-06
387
  },
388
  "TrainerController._save_models": {
389
- "total": 0.5215067739998176,
390
  "count": 1,
391
- "self": 0.008645491999686783,
392
  "children": {
393
  "RLTrainer._checkpoint": {
394
- "total": 0.5128612820001308,
395
  "count": 1,
396
- "self": 0.5128612820001308
397
  }
398
  }
399
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.1824750900268555,
6
+ "min": 3.1547484397888184,
7
+ "max": 3.2956900596618652,
8
+ "count": 100
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 88701.9453125,
12
+ "min": 23412.0703125,
13
+ "max": 114764.3203125,
14
+ "count": 100
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 860.5,
18
+ "min": 489.9,
19
  "max": 999.0,
20
+ "count": 100
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 20652.0,
24
+ "min": 14644.0,
25
+ "max": 27616.0,
26
+ "count": 100
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1200.78991806887,
30
+ "min": 1197.0440605645447,
31
+ "max": 1207.1172065682176,
32
+ "count": 90
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 4803.15967227548,
36
+ "min": 2394.0881211290894,
37
+ "max": 16784.708841766012,
38
+ "count": 90
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 999684.0,
42
+ "min": 9824.0,
43
+ "max": 999684.0,
44
+ "count": 100
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 999684.0,
48
+ "min": 9824.0,
49
+ "max": 999684.0,
50
+ "count": 100
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.00797598622739315,
54
+ "min": -0.036553021520376205,
55
+ "max": 0.05947311595082283,
56
+ "count": 100
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.0957118347287178,
60
+ "min": -0.438421368598938,
61
+ "max": 0.8325973749160767,
62
+ "count": 100
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.006179752293974161,
66
+ "min": -0.022581540048122406,
67
+ "max": 0.05948488041758537,
68
+ "count": 100
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.07415702939033508,
72
+ "min": -0.27457916736602783,
73
+ "max": 0.8327765464782715,
74
+ "count": 100
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 100
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 100
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.16666666666666666,
90
+ "min": -0.5860000000550196,
91
+ "max": 0.38087058768552895,
92
+ "count": 100
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -2.0,
96
+ "min": -8.0,
97
+ "max": 6.474799990653992,
98
+ "count": 100
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.16666666666666666,
102
+ "min": -0.5860000000550196,
103
+ "max": 0.38087058768552895,
104
+ "count": 100
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -2.0,
108
+ "min": -8.0,
109
+ "max": 6.474799990653992,
110
+ "count": 100
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 100
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 100
123
  },
124
  "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.012221555140179892,
126
+ "min": 0.006795583742981156,
127
+ "max": 0.016645218633736174,
128
+ "count": 46
129
  },
130
  "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.012221555140179892,
132
+ "min": 0.006795583742981156,
133
+ "max": 0.016645218633736174,
134
+ "count": 46
135
  },
136
  "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.003237667710830768,
138
+ "min": 8.194062053613985e-05,
139
+ "max": 0.01861500459102293,
140
+ "count": 46
141
  },
142
  "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.003237667710830768,
144
+ "min": 8.194062053613985e-05,
145
+ "max": 0.01861500459102293,
146
+ "count": 46
147
  },
148
  "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.00324154964958628,
150
+ "min": 7.848465102142655e-05,
151
+ "max": 0.009435744381820162,
152
+ "count": 46
153
  },
154
  "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.00324154964958628,
156
+ "min": 7.848465102142655e-05,
157
+ "max": 0.009435744381820162,
158
+ "count": 46
159
  },
160
  "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0006,
162
+ "min": 0.0006,
163
+ "max": 0.0006,
164
+ "count": 46
165
  },
166
  "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0006,
168
+ "min": 0.0006,
169
+ "max": 0.0006,
170
+ "count": 46
171
  },
172
  "SoccerTwos.Policy.Epsilon.mean": {
173
  "value": 0.20000000000000007,
174
  "min": 0.20000000000000007,
175
  "max": 0.20000000000000007,
176
+ "count": 46
177
  },
178
  "SoccerTwos.Policy.Epsilon.sum": {
179
  "value": 0.20000000000000007,
180
  "min": 0.20000000000000007,
181
  "max": 0.20000000000000007,
182
+ "count": 46
183
  },
184
  "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005,
186
+ "min": 0.005,
187
+ "max": 0.005,
188
+ "count": 46
189
  },
190
  "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005,
192
+ "min": 0.005,
193
+ "max": 0.005,
194
+ "count": 46
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1697686348",
200
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
201
  "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "1.1.0.dev0",
 
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.0.1+cu118",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1697688565"
208
  },
209
+ "total": 2217.164994551,
210
  "count": 1,
211
+ "self": 0.4259129499996561,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.07464664500002982,
215
  "count": 1,
216
+ "self": 0.07464664500002982
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 2216.664434956,
220
  "count": 1,
221
+ "self": 1.6753877999994984,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 4.416130657000224,
225
+ "count": 5,
226
+ "self": 4.416130657000224
227
  },
228
  "TrainerController.advance": {
229
+ "total": 2210.3573846880004,
230
+ "count": 65069,
231
+ "self": 1.8022751490188966,
232
  "children": {
233
  "env_step": {
234
+ "total": 1823.0047769609614,
235
+ "count": 65069,
236
+ "self": 1406.1171325439245,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 415.8875872410355,
240
+ "count": 65069,
241
+ "self": 11.887741108043144,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 403.99984613299233,
245
+ "count": 129182,
246
+ "self": 403.99984613299233
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 1.0000571760013486,
252
+ "count": 65069,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 2212.1702933349934,
257
+ "count": 65069,
258
  "is_parallel": true,
259
+ "self": 1033.889048864969,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.0044236590000537035,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0009960950001186575,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.003427563999935046,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.003427563999935046
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.0418704440000397,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0012168680000286258,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0008716350000099737,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.0008716350000099737
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.035724202000039895,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.035724202000039895
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.004057738999961202,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0006634809998899982,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.003394258000071204,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.003394258000071204
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 1178.2684012030245,
319
+ "count": 65068,
320
  "is_parallel": true,
321
+ "self": 75.30102161908849,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 49.89441047398384,
325
+ "count": 65068,
326
  "is_parallel": true,
327
+ "self": 49.89441047398384
328
  },
329
  "communicator.exchange": {
330
+ "total": 818.6866904860156,
331
+ "count": 65068,
332
  "is_parallel": true,
333
+ "self": 818.6866904860156
334
  },
335
  "steps_from_proto": {
336
+ "total": 234.38627862393668,
337
+ "count": 130136,
338
  "is_parallel": true,
339
+ "self": 37.99782386399312,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 196.38845475994356,
343
+ "count": 520544,
344
  "is_parallel": true,
345
+ "self": 196.38845475994356
346
  }
347
  }
348
  }
349
  }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.012843266999880143,
353
+ "count": 8,
354
+ "is_parallel": true,
355
+ "self": 0.002305757999351954,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.010537509000528189,
359
+ "count": 32,
360
+ "is_parallel": true,
361
+ "self": 0.010537509000528189
362
+ }
363
+ }
364
  }
365
  }
366
  }
 
369
  }
370
  },
371
  "trainer_advance": {
372
+ "total": 385.55033257802,
373
+ "count": 65069,
374
+ "self": 14.281712731008213,
375
  "children": {
376
  "process_trajectory": {
377
+ "total": 109.3654763670126,
378
+ "count": 65069,
379
+ "self": 108.84511364601275,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 0.5203627209998558,
383
+ "count": 2,
384
+ "self": 0.5203627209998558
385
+ }
386
+ }
387
  },
388
  "_update_policy": {
389
+ "total": 261.9031434799992,
390
+ "count": 46,
391
+ "self": 161.58336632699843,
392
  "children": {
393
  "TorchPOCAOptimizer.update": {
394
+ "total": 100.31977715300076,
395
+ "count": 690,
396
+ "self": 100.31977715300076
397
  }
398
  }
399
  }
 
402
  }
403
  },
404
  "trainer_threads": {
405
+ "total": 1.0740000107034575e-06,
406
  "count": 1,
407
+ "self": 1.0740000107034575e-06
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.2155307369998809,
411
  "count": 1,
412
+ "self": 0.001797785000235308,
413
  "children": {
414
  "RLTrainer._checkpoint": {
415
+ "total": 0.2137329519996456,
416
  "count": 1,
417
+ "self": 0.2137329519996456
418
  }
419
  }
420
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,42 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 1200.011282228457,
4
  "checkpoints": [
5
  {
6
- "steps": 166288,
7
- "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-166288.onnx",
8
  "reward": 0.0,
9
- "creation_time": 1697685594.2369165,
10
  "auxillary_file_paths": [
11
- "results/SoccerTwos/SoccerTwos/SoccerTwos-166288.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ]
13
  }
14
  ],
 
15
  "final_checkpoint": {
16
- "steps": 166288,
17
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
18
  "reward": 0.0,
19
- "creation_time": 1697685594.2369165,
20
  "auxillary_file_paths": [
21
- "results/SoccerTwos/SoccerTwos/SoccerTwos-166288.pt"
22
  ]
23
  }
24
  },
 
1
  {
2
  "SoccerTwos": {
 
3
  "checkpoints": [
4
  {
5
+ "steps": 499090,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499090.onnx",
7
  "reward": 0.0,
8
+ "creation_time": 1697687438.9836857,
9
  "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-499090.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 999684,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-999684.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1697688564.6902308,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-999684.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 1001494,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001494.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1697688565.088375,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1001494.pt"
29
  ]
30
  }
31
  ],
32
+ "elo": 1200.6642707649974,
33
  "final_checkpoint": {
34
+ "steps": 1001494,
35
  "file_path": "results/SoccerTwos/SoccerTwos.onnx",
36
  "reward": 0.0,
37
+ "creation_time": 1697688565.088375,
38
  "auxillary_file_paths": [
39
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-1001494.pt"
40
  ]
41
  }
42
  },