Hugging Face's logo

YuvanKumar
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files
xet
Metrics Community
Ankit Kumar commited on
Commit
ec75bf3
·
1 Parent(s): 03ad24b

First Push

Browse files
Files changed (6) hide show
  1. SoccerTwos/events.out.tfevents.1699096825.b0236b23e47a.4493.0 +3 -0
  2. config.json +1 -1
  3. configuration.yaml +1 -1
  4. run_logs/Player-0.log +57 -17
  5. run_logs/timers.json +221 -137
  6. run_logs/training_status.json +1 -21
SoccerTwos/events.out.tfevents.1699096825.b0236b23e47a.4493.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261618376b5ef4e8fb6572a4cfe5c18c9b829efb8f4f5e32bebf068547a02971
3
+ size 65575
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.002, "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": 750000000, "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": "/content/ml-agents/training-envs-executables/linux/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": "SoccerTwos0", "initialize_from": null, "load_model": false, "resume": false, "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": 0.002, "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": 750000000, "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": "/content/ml-agents/training-envs-executables/linux/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": "SoccerTwos01", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -70,7 +70,7 @@ engine_settings:
70
  no_graphics: true
71
  environment_parameters: null
72
  checkpoint_settings:
73
- run_id: SoccerTwos0
74
  initialize_from: null
75
  load_model: false
76
  resume: false
 
70
  no_graphics: true
71
  environment_parameters: null
72
  checkpoint_settings:
73
+ run_id: SoccerTwos01
74
  initialize_from: null
75
  load_model: false
76
  resume: false
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
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 0.076 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)
@@ -56,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
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: 0.672214 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
@@ -67,12 +67,52 @@ TOO LONG
67
  TOO LONG
68
  TOO LONG
69
  TOO LONG
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  Setting up 1 worker threads for Enlighten.
 
 
 
 
71
  Memory Statistics:
72
  [ALLOC_TEMP_TLS] TLS Allocator
73
  StackAllocators :
74
  [ALLOC_TEMP_MAIN]
75
- Peak usage frame count: [8.0 KB-16.0 KB]: 589 frames, [2.0 MB-4.0 MB]: 1 frames
76
  Initial Block Size 4.0 MB
77
  Current Block Size 4.0 MB
78
  Peak Allocated Bytes 2.1 MB
@@ -188,23 +228,23 @@ Memory Statistics:
188
  Peak Allocated Bytes 0 B
189
  Overflow Count 0
190
  [ALLOC_DEFAULT] Dual Thread Allocator
191
- Peak main deferred allocation count 4
192
  [ALLOC_BUCKET]
193
  Large Block size 4.0 MB
194
  Used Block count 1
195
  Peak Allocated bytes 1.0 MB
196
  [ALLOC_DEFAULT_MAIN]
197
- Peak usage frame count: [4.0 MB-8.0 MB]: 590 frames
198
  Requested Block Size 16.0 MB
199
  Peak Block count 1
200
- Peak Allocated memory 4.6 MB
201
- Peak Large allocation bytes 0 B
202
  [ALLOC_DEFAULT_THREAD]
203
- Peak usage frame count: [16.0 MB-32.0 MB]: 590 frames
204
  Requested Block Size 16.0 MB
205
  Peak Block count 1
206
- Peak Allocated memory 17.5 MB
207
- Peak Large allocation bytes 16.0 MB
208
  [ALLOC_TEMP_JOB_1_FRAME]
209
  Initial Block Size 2.0 MB
210
  Used Block Count 1
@@ -232,13 +272,13 @@ Memory Statistics:
232
  Used Block count 1
233
  Peak Allocated bytes 1.0 MB
234
  [ALLOC_GFX_MAIN]
235
- Peak usage frame count: [32.0 KB-64.0 KB]: 589 frames, [64.0 KB-128.0 KB]: 1 frames
236
  Requested Block Size 16.0 MB
237
  Peak Block count 1
238
  Peak Allocated memory 65.6 KB
239
  Peak Large allocation bytes 0 B
240
  [ALLOC_GFX_THREAD]
241
- Peak usage frame count: [128.0 KB-256.0 KB]: 590 frames
242
  Requested Block Size 16.0 MB
243
  Peak Block count 1
244
  Peak Allocated memory 173.5 KB
@@ -250,16 +290,16 @@ Memory Statistics:
250
  Used Block count 1
251
  Peak Allocated bytes 1.0 MB
252
  [ALLOC_CACHEOBJECTS_MAIN]
253
- Peak usage frame count: [0.5 MB-1.0 MB]: 590 frames
254
  Requested Block Size 4.0 MB
255
  Peak Block count 1
256
  Peak Allocated memory 0.6 MB
257
  Peak Large allocation bytes 0 B
258
  [ALLOC_CACHEOBJECTS_THREAD]
259
- Peak usage frame count: [0.5 MB-1.0 MB]: 589 frames, [4.0 MB-8.0 MB]: 1 frames
260
  Requested Block Size 4.0 MB
261
  Peak Block count 2
262
- Peak Allocated memory 4.4 MB
263
  Peak Large allocation bytes 0 B
264
  [ALLOC_TYPETREE] Dual Thread Allocator
265
  Peak main deferred allocation count 0
@@ -268,13 +308,13 @@ Memory Statistics:
268
  Used Block count 1
269
  Peak Allocated bytes 1.0 MB
270
  [ALLOC_TYPETREE_MAIN]
271
- Peak usage frame count: [0-1.0 KB]: 590 frames
272
  Requested Block Size 2.0 MB
273
  Peak Block count 1
274
  Peak Allocated memory 1.0 KB
275
  Peak Large allocation bytes 0 B
276
  [ALLOC_TYPETREE_THREAD]
277
- Peak usage frame count: [1.0 KB-2.0 KB]: 589 frames, [2.0 KB-4.0 KB]: 1 frames
278
  Requested Block Size 2.0 MB
279
  Peak Block count 1
280
  Peak Allocated memory 2.2 KB
 
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 0.112 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: 0.831598 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
 
67
  TOO LONG
68
  TOO LONG
69
  TOO LONG
70
+ TOO LONG
71
+ TOO LONG
72
+ TOO LONG
73
+ TOO LONG
74
+ TOO LONG
75
+ TOO LONG
76
+ TOO LONG
77
+ TOO LONG
78
+ TOO LONG
79
+ TOO LONG
80
+ TOO LONG
81
+ TOO LONG
82
+ TOO LONG
83
+ TOO LONG
84
+ TOO LONG
85
+ TOO LONG
86
+ TOO LONG
87
+ TOO LONG
88
+ TOO LONG
89
+ TOO LONG
90
+ TOO LONG
91
+ TOO LONG
92
+ TOO LONG
93
+ TOO LONG
94
+ TOO LONG
95
+ TOO LONG
96
+ TOO LONG
97
+ TOO LONG
98
+ TOO LONG
99
+ TOO LONG
100
+ TOO LONG
101
+ TOO LONG
102
+ TOO LONG
103
+ TOO LONG
104
+ TOO LONG
105
+ TOO LONG
106
  Setting up 1 worker threads for Enlighten.
107
+ abort_threads: Failed aborting id: 0x795bc6df9640, mono_thread_manage will ignore it
108
+
109
+ abort_threads: Failed aborting id: 0x795bc6ffa640, mono_thread_manage will ignore it
110
+
111
  Memory Statistics:
112
  [ALLOC_TEMP_TLS] TLS Allocator
113
  StackAllocators :
114
  [ALLOC_TEMP_MAIN]
115
+ Peak usage frame count: [8.0 KB-16.0 KB]: 2110 frames, [2.0 MB-4.0 MB]: 1 frames
116
  Initial Block Size 4.0 MB
117
  Current Block Size 4.0 MB
118
  Peak Allocated Bytes 2.1 MB
 
228
  Peak Allocated Bytes 0 B
229
  Overflow Count 0
230
  [ALLOC_DEFAULT] Dual Thread Allocator
231
+ Peak main deferred allocation count 2
232
  [ALLOC_BUCKET]
233
  Large Block size 4.0 MB
234
  Used Block count 1
235
  Peak Allocated bytes 1.0 MB
236
  [ALLOC_DEFAULT_MAIN]
237
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2111 frames
238
  Requested Block Size 16.0 MB
239
  Peak Block count 1
240
+ Peak Allocated memory 20.7 MB
241
+ Peak Large allocation bytes 16.0 MB
242
  [ALLOC_DEFAULT_THREAD]
243
+ Peak usage frame count: [1.0 MB-2.0 MB]: 2111 frames
244
  Requested Block Size 16.0 MB
245
  Peak Block count 1
246
+ Peak Allocated memory 1.5 MB
247
+ Peak Large allocation bytes 0 B
248
  [ALLOC_TEMP_JOB_1_FRAME]
249
  Initial Block Size 2.0 MB
250
  Used Block Count 1
 
272
  Used Block count 1
273
  Peak Allocated bytes 1.0 MB
274
  [ALLOC_GFX_MAIN]
275
+ Peak usage frame count: [32.0 KB-64.0 KB]: 2110 frames, [64.0 KB-128.0 KB]: 1 frames
276
  Requested Block Size 16.0 MB
277
  Peak Block count 1
278
  Peak Allocated memory 65.6 KB
279
  Peak Large allocation bytes 0 B
280
  [ALLOC_GFX_THREAD]
281
+ Peak usage frame count: [128.0 KB-256.0 KB]: 2111 frames
282
  Requested Block Size 16.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 173.5 KB
 
290
  Used Block count 1
291
  Peak Allocated bytes 1.0 MB
292
  [ALLOC_CACHEOBJECTS_MAIN]
293
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2111 frames
294
  Requested Block Size 4.0 MB
295
  Peak Block count 1
296
  Peak Allocated memory 0.6 MB
297
  Peak Large allocation bytes 0 B
298
  [ALLOC_CACHEOBJECTS_THREAD]
299
+ Peak usage frame count: [0.5 MB-1.0 MB]: 2110 frames, [4.0 MB-8.0 MB]: 1 frames
300
  Requested Block Size 4.0 MB
301
  Peak Block count 2
302
+ Peak Allocated memory 4.5 MB
303
  Peak Large allocation bytes 0 B
304
  [ALLOC_TYPETREE] Dual Thread Allocator
305
  Peak main deferred allocation count 0
 
308
  Used Block count 1
309
  Peak Allocated bytes 1.0 MB
310
  [ALLOC_TYPETREE_MAIN]
311
+ Peak usage frame count: [0-1.0 KB]: 2111 frames
312
  Requested Block Size 2.0 MB
313
  Peak Block count 1
314
  Peak Allocated memory 1.0 KB
315
  Peak Large allocation bytes 0 B
316
  [ALLOC_TYPETREE_THREAD]
317
+ Peak usage frame count: [1.0 KB-2.0 KB]: 2110 frames, [2.0 KB-4.0 KB]: 1 frames
318
  Requested Block Size 2.0 MB
319
  Peak Block count 1
320
  Peak Allocated memory 2.2 KB
run_logs/timers.json CHANGED
@@ -2,189 +2,261 @@
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 3.295701265335083,
6
- "min": 3.295701265335083,
7
- "max": 3.295701265335083,
8
- "count": 1
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 105462.4375,
12
- "min": 105462.4375,
13
- "max": 105462.4375,
14
- "count": 1
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 775.2222222222222,
18
- "min": 775.2222222222222,
19
- "max": 775.2222222222222,
20
- "count": 1
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 27908.0,
24
- "min": 27908.0,
25
- "max": 27908.0,
26
- "count": 1
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 1201.2421091626256,
30
- "min": 1201.2421091626256,
31
- "max": 1201.2421091626256,
32
- "count": 1
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 7207.452654975754,
36
- "min": 7207.452654975754,
37
- "max": 7207.452654975754,
38
- "count": 1
39
  },
40
  "SoccerTwos.Step.mean": {
41
- "value": 9972.0,
42
- "min": 9972.0,
43
- "max": 9972.0,
44
- "count": 1
45
  },
46
  "SoccerTwos.Step.sum": {
47
- "value": 9972.0,
48
- "min": 9972.0,
49
- "max": 9972.0,
50
- "count": 1
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": -0.02923949994146824,
54
- "min": -0.02923949994146824,
55
- "max": -0.02923949994146824,
56
- "count": 1
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": -0.40935298800468445,
60
- "min": -0.40935298800468445,
61
- "max": -0.40935298800468445,
62
- "count": 1
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": -0.029252752661705017,
66
- "min": -0.029252752661705017,
67
- "max": -0.029252752661705017,
68
- "count": 1
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": -0.40953853726387024,
72
- "min": -0.40953853726387024,
73
- "max": -0.40953853726387024,
74
- "count": 1
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
- "count": 1
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
- "count": 1
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
- "value": 0.06317142929349627,
90
- "min": 0.06317142929349627,
91
- "max": 0.06317142929349627,
92
- "count": 1
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
- "value": 0.8844000101089478,
96
- "min": 0.8844000101089478,
97
- "max": 0.8844000101089478,
98
- "count": 1
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
- "value": 0.06317142929349627,
102
- "min": 0.06317142929349627,
103
- "max": 0.06317142929349627,
104
- "count": 1
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
- "value": 0.8844000101089478,
108
- "min": 0.8844000101089478,
109
- "max": 0.8844000101089478,
110
- "count": 1
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
- "count": 1
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
- "count": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  }
124
  },
125
  "metadata": {
126
  "timer_format_version": "0.1.0",
127
- "start_time_seconds": "1699096723",
128
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
129
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=/content/ml-agents/training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos0 --no-graphics",
130
  "mlagents_version": "1.1.0.dev0",
131
  "mlagents_envs_version": "1.1.0.dev0",
132
  "communication_protocol_version": "1.5.0",
133
  "pytorch_version": "2.1.0+cu118",
134
  "numpy_version": "1.23.5",
135
- "end_time_seconds": "1699096782"
136
  },
137
- "total": 58.24280296799998,
138
  "count": 1,
139
- "self": 0.24806138300004932,
140
  "children": {
141
  "run_training.setup": {
142
- "total": 0.07365783000000192,
143
  "count": 1,
144
- "self": 0.07365783000000192
145
  },
146
  "TrainerController.start_learning": {
147
- "total": 57.92108375499993,
148
  "count": 1,
149
- "self": 0.04190139500087753,
150
  "children": {
151
  "TrainerController._reset_env": {
152
- "total": 3.505634599000018,
153
  "count": 1,
154
- "self": 3.505634599000018
155
  },
156
  "TrainerController.advance": {
157
- "total": 54.18094058899908,
158
- "count": 1972,
159
- "self": 0.04610147799223796,
160
  "children": {
161
  "env_step": {
162
- "total": 52.03431364800417,
163
- "count": 1972,
164
- "self": 39.502977546005695,
165
  "children": {
166
  "SubprocessEnvManager._take_step": {
167
- "total": 12.506262596000624,
168
- "count": 1972,
169
- "self": 0.29341999000132546,
170
  "children": {
171
  "TorchPolicy.evaluate": {
172
- "total": 12.212842605999299,
173
- "count": 3930,
174
- "self": 12.212842605999299
175
  }
176
  }
177
  },
178
  "workers": {
179
- "total": 0.025073505997852408,
180
- "count": 1971,
181
  "self": 0.0,
182
  "children": {
183
  "worker_root": {
184
- "total": 57.65285638399769,
185
- "count": 1971,
186
  "is_parallel": true,
187
- "self": 23.914499940997644,
188
  "children": {
189
  "run_training.setup": {
190
  "total": 0.0,
@@ -193,48 +265,48 @@
193
  "self": 0.0,
194
  "children": {
195
  "steps_from_proto": {
196
- "total": 0.004111491999992722,
197
  "count": 2,
198
  "is_parallel": true,
199
- "self": 0.0008768579998559289,
200
  "children": {
201
  "_process_rank_one_or_two_observation": {
202
- "total": 0.0032346340001367935,
203
  "count": 8,
204
  "is_parallel": true,
205
- "self": 0.0032346340001367935
206
  }
207
  }
208
  },
209
  "UnityEnvironment.step": {
210
- "total": 0.03874437499996475,
211
  "count": 1,
212
  "is_parallel": true,
213
- "self": 0.0012145509999754722,
214
  "children": {
215
  "UnityEnvironment._generate_step_input": {
216
- "total": 0.0008111319999670741,
217
  "count": 1,
218
  "is_parallel": true,
219
- "self": 0.0008111319999670741
220
  },
221
  "communicator.exchange": {
222
- "total": 0.03315890299995772,
223
  "count": 1,
224
  "is_parallel": true,
225
- "self": 0.03315890299995772
226
  },
227
  "steps_from_proto": {
228
- "total": 0.003559789000064484,
229
  "count": 2,
230
  "is_parallel": true,
231
- "self": 0.0006073999999216539,
232
  "children": {
233
  "_process_rank_one_or_two_observation": {
234
- "total": 0.00295238900014283,
235
  "count": 8,
236
  "is_parallel": true,
237
- "self": 0.00295238900014283
238
  }
239
  }
240
  }
@@ -243,34 +315,34 @@
243
  }
244
  },
245
  "UnityEnvironment.step": {
246
- "total": 33.73835644300004,
247
- "count": 1970,
248
  "is_parallel": true,
249
- "self": 2.2007520200004365,
250
  "children": {
251
  "UnityEnvironment._generate_step_input": {
252
- "total": 1.439469144000327,
253
- "count": 1970,
254
  "is_parallel": true,
255
- "self": 1.439469144000327
256
  },
257
  "communicator.exchange": {
258
- "total": 23.371878775001164,
259
- "count": 1970,
260
  "is_parallel": true,
261
- "self": 23.371878775001164
262
  },
263
  "steps_from_proto": {
264
- "total": 6.7262565039981155,
265
- "count": 3940,
266
  "is_parallel": true,
267
- "self": 1.0663492169982192,
268
  "children": {
269
  "_process_rank_one_or_two_observation": {
270
- "total": 5.659907286999896,
271
- "count": 15760,
272
  "is_parallel": true,
273
- "self": 5.659907286999896
274
  }
275
  }
276
  }
@@ -283,33 +355,45 @@
283
  }
284
  },
285
  "trainer_advance": {
286
- "total": 2.1005254630026684,
287
- "count": 1971,
288
- "self": 0.20247993100224448,
289
  "children": {
290
  "process_trajectory": {
291
- "total": 1.898045532000424,
292
- "count": 1971,
293
- "self": 1.898045532000424
 
 
 
 
 
 
 
 
 
 
 
 
294
  }
295
  }
296
  }
297
  }
298
  },
299
  "trainer_threads": {
300
- "total": 1.217999965774652e-06,
301
  "count": 1,
302
- "self": 1.217999965774652e-06
303
  },
304
  "TrainerController._save_models": {
305
- "total": 0.19260595399998692,
306
  "count": 1,
307
- "self": 0.0021166769998899326,
308
  "children": {
309
  "RLTrainer._checkpoint": {
310
- "total": 0.190489277000097,
311
  "count": 1,
312
- "self": 0.190489277000097
313
  }
314
  }
315
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.2614316940307617,
6
+ "min": 3.258707284927368,
7
+ "max": 3.295718193054199,
8
+ "count": 10
9
  },
10
  "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 89650.234375,
12
+ "min": 30292.70703125,
13
+ "max": 105462.984375,
14
+ "count": 10
15
  },
16
  "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 883.1666666666666,
18
+ "min": 642.625,
19
+ "max": 999.0,
20
+ "count": 10
21
  },
22
  "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 21196.0,
24
+ "min": 12328.0,
25
+ "max": 27864.0,
26
+ "count": 10
27
  },
28
  "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1200.6875594647793,
30
+ "min": 1200.6875594647793,
31
+ "max": 1203.943047306674,
32
+ "count": 8
33
  },
34
  "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 7204.125356788676,
36
+ "min": 2403.8360569975775,
37
+ "max": 9623.964240807352,
38
+ "count": 8
39
  },
40
  "SoccerTwos.Step.mean": {
41
+ "value": 99390.0,
42
+ "min": 9948.0,
43
+ "max": 99390.0,
44
+ "count": 10
45
  },
46
  "SoccerTwos.Step.sum": {
47
+ "value": 99390.0,
48
+ "min": 9948.0,
49
+ "max": 99390.0,
50
+ "count": 10
51
  },
52
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.03879609331488609,
54
+ "min": -0.10664743185043335,
55
+ "max": -0.03879609331488609,
56
+ "count": 10
57
  },
58
  "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.42675700783729553,
60
+ "min": -1.1396600008010864,
61
+ "max": -0.42675700783729553,
62
+ "count": 10
63
  },
64
  "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.03732283413410187,
66
+ "min": -0.05642535164952278,
67
+ "max": -0.03732283413410187,
68
+ "count": 10
69
  },
70
  "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.41055116057395935,
72
+ "min": -0.8185520172119141,
73
+ "max": -0.40887296199798584,
74
+ "count": 10
75
  },
76
  "SoccerTwos.Environment.CumulativeReward.mean": {
77
  "value": 0.0,
78
  "min": 0.0,
79
  "max": 0.0,
80
+ "count": 10
81
  },
82
  "SoccerTwos.Environment.CumulativeReward.sum": {
83
  "value": 0.0,
84
  "min": 0.0,
85
  "max": 0.0,
86
+ "count": 10
87
  },
88
  "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": -0.2970909096977927,
90
+ "min": -0.36251764437731576,
91
+ "max": 0.17113332947095236,
92
+ "count": 10
93
  },
94
  "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -3.26800000667572,
96
+ "min": -6.162799954414368,
97
+ "max": 2.0535999536514282,
98
+ "count": 10
99
  },
100
  "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.2970909096977927,
102
+ "min": -0.36251764437731576,
103
+ "max": 0.17113332947095236,
104
+ "count": 10
105
  },
106
  "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -3.26800000667572,
108
+ "min": -6.162799954414368,
109
+ "max": 2.0535999536514282,
110
+ "count": 10
111
  },
112
  "SoccerTwos.IsTraining.mean": {
113
  "value": 1.0,
114
  "min": 1.0,
115
  "max": 1.0,
116
+ "count": 10
117
  },
118
  "SoccerTwos.IsTraining.sum": {
119
  "value": 1.0,
120
  "min": 1.0,
121
  "max": 1.0,
122
+ "count": 10
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.016862712742295116,
126
+ "min": 0.01494209394052935,
127
+ "max": 0.020022764914513876,
128
+ "count": 4
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.016862712742295116,
132
+ "min": 0.01494209394052935,
133
+ "max": 0.020022764914513876,
134
+ "count": 4
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.0019297421560622752,
138
+ "min": 0.0008788986102445051,
139
+ "max": 2.080857078152864,
140
+ "count": 4
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.0019297421560622752,
144
+ "min": 0.0008788986102445051,
145
+ "max": 2.080857078152864,
146
+ "count": 4
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.0019658890281183026,
150
+ "min": 0.0013164583060036724,
151
+ "max": 2.0529311431649453,
152
+ "count": 4
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.0019658890281183026,
156
+ "min": 0.0013164583060036724,
157
+ "max": 2.0529311431649453,
158
+ "count": 4
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0020000000000000005,
162
+ "min": 0.0020000000000000005,
163
+ "max": 0.0020000000000000005,
164
+ "count": 4
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0020000000000000005,
168
+ "min": 0.0020000000000000005,
169
+ "max": 0.0020000000000000005,
170
+ "count": 4
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 4
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 4
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 4
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 4
195
  }
196
  },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1699096824",
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=/content/ml-agents/training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos01 --no-graphics",
202
  "mlagents_version": "1.1.0.dev0",
203
  "mlagents_envs_version": "1.1.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.1.0+cu118",
206
  "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1699097055"
208
  },
209
+ "total": 231.51909745199998,
210
  "count": 1,
211
+ "self": 0.433240799000032,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.068995616000052,
215
  "count": 1,
216
+ "self": 0.068995616000052
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 231.0168610369999,
220
  "count": 1,
221
+ "self": 0.151787955996042,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 4.105791149999959,
225
  "count": 1,
226
+ "self": 4.105791149999959
227
  },
228
  "TrainerController.advance": {
229
+ "total": 226.75851142400393,
230
+ "count": 7079,
231
+ "self": 0.17550149299711393,
232
  "children": {
233
  "env_step": {
234
+ "total": 185.79979378700045,
235
+ "count": 7079,
236
+ "self": 142.23789582400184,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
+ "total": 43.46966568900291,
240
+ "count": 7079,
241
+ "self": 1.2732977140242383,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
+ "total": 42.19636797497867,
245
+ "count": 14072,
246
+ "self": 42.19636797497867
247
  }
248
  }
249
  },
250
  "workers": {
251
+ "total": 0.09223227399570533,
252
+ "count": 7078,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
+ "total": 230.68744517500602,
257
+ "count": 7078,
258
  "is_parallel": true,
259
+ "self": 110.80680951599982,
260
  "children": {
261
  "run_training.setup": {
262
  "total": 0.0,
 
265
  "self": 0.0,
266
  "children": {
267
  "steps_from_proto": {
268
+ "total": 0.004338862000054178,
269
  "count": 2,
270
  "is_parallel": true,
271
+ "self": 0.0009452800001099604,
272
  "children": {
273
  "_process_rank_one_or_two_observation": {
274
+ "total": 0.0033935819999442174,
275
  "count": 8,
276
  "is_parallel": true,
277
+ "self": 0.0033935819999442174
278
  }
279
  }
280
  },
281
  "UnityEnvironment.step": {
282
+ "total": 0.0403638760000149,
283
  "count": 1,
284
  "is_parallel": true,
285
+ "self": 0.0011478690000785718,
286
  "children": {
287
  "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0009303319999389714,
289
  "count": 1,
290
  "is_parallel": true,
291
+ "self": 0.0009303319999389714
292
  },
293
  "communicator.exchange": {
294
+ "total": 0.03501296700005696,
295
  "count": 1,
296
  "is_parallel": true,
297
+ "self": 0.03501296700005696
298
  },
299
  "steps_from_proto": {
300
+ "total": 0.003272707999940394,
301
  "count": 2,
302
  "is_parallel": true,
303
+ "self": 0.0005610439999372829,
304
  "children": {
305
  "_process_rank_one_or_two_observation": {
306
+ "total": 0.002711664000003111,
307
  "count": 8,
308
  "is_parallel": true,
309
+ "self": 0.002711664000003111
310
  }
311
  }
312
  }
 
315
  }
316
  },
317
  "UnityEnvironment.step": {
318
+ "total": 119.8806356590062,
319
+ "count": 7077,
320
  "is_parallel": true,
321
+ "self": 7.849778665020153,
322
  "children": {
323
  "UnityEnvironment._generate_step_input": {
324
+ "total": 5.165152892002652,
325
+ "count": 7077,
326
  "is_parallel": true,
327
+ "self": 5.165152892002652
328
  },
329
  "communicator.exchange": {
330
+ "total": 83.09441377599637,
331
+ "count": 7077,
332
  "is_parallel": true,
333
+ "self": 83.09441377599637
334
  },
335
  "steps_from_proto": {
336
+ "total": 23.771290325987025,
337
+ "count": 14154,
338
  "is_parallel": true,
339
+ "self": 3.8716112029813985,
340
  "children": {
341
  "_process_rank_one_or_two_observation": {
342
+ "total": 19.899679123005626,
343
+ "count": 56616,
344
  "is_parallel": true,
345
+ "self": 19.899679123005626
346
  }
347
  }
348
  }
 
355
  }
356
  },
357
  "trainer_advance": {
358
+ "total": 40.78321614400636,
359
+ "count": 7078,
360
+ "self": 1.2156955810019099,
361
  "children": {
362
  "process_trajectory": {
363
+ "total": 9.969533540004363,
364
+ "count": 7078,
365
+ "self": 9.969533540004363
366
+ },
367
+ "_update_policy": {
368
+ "total": 29.597987023000087,
369
+ "count": 5,
370
+ "self": 17.846319298001617,
371
+ "children": {
372
+ "TorchPOCAOptimizer.update": {
373
+ "total": 11.75166772499847,
374
+ "count": 150,
375
+ "self": 11.75166772499847
376
+ }
377
+ }
378
  }
379
  }
380
  }
381
  }
382
  },
383
  "trainer_threads": {
384
+ "total": 1.13999999484804e-06,
385
  "count": 1,
386
+ "self": 1.13999999484804e-06
387
  },
388
  "TrainerController._save_models": {
389
+ "total": 0.0007693669999753183,
390
  "count": 1,
391
+ "self": 4.186799992567103e-05,
392
  "children": {
393
  "RLTrainer._checkpoint": {
394
+ "total": 0.0007274990000496473,
395
  "count": 1,
396
+ "self": 0.0007274990000496473
397
  }
398
  }
399
  }
run_logs/training_status.json CHANGED
@@ -1,26 +1,6 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 1202.9615075645554,
4
- "checkpoints": [
5
- {
6
- "steps": 18984,
7
- "file_path": "results/SoccerTwos0/SoccerTwos/SoccerTwos-18984.onnx",
8
- "reward": 0.0,
9
- "creation_time": 1699096781.9356186,
10
- "auxillary_file_paths": [
11
- "results/SoccerTwos0/SoccerTwos/SoccerTwos-18984.pt"
12
- ]
13
- }
14
- ],
15
- "final_checkpoint": {
16
- "steps": 18984,
17
- "file_path": "results/SoccerTwos0/SoccerTwos.onnx",
18
- "reward": 0.0,
19
- "creation_time": 1699096781.9356186,
20
- "auxillary_file_paths": [
21
- "results/SoccerTwos0/SoccerTwos/SoccerTwos-18984.pt"
22
- ]
23
- }
24
  },
25
  "metadata": {
26
  "stats_format_version": "0.3.0",
 
1
  {
2
  "SoccerTwos": {
3
+ "elo": 1200.9371342856173
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  },
5
  "metadata": {
6
  "stats_format_version": "0.3.0",