Hugging Face's logo

brettgoehre
/
poca-SoccerTwosMemory

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
brettgoehre commited on
Commit
e6089b0
·
verified ·
1 Parent(s): b60b8db

Fifth Push

Browse files
Files changed (12) hide show
  1. SoccerTwos.onnx +1 -1
  2. SoccerTwos/SoccerTwos-28499990.onnx +3 -0
  3. SoccerTwos/SoccerTwos-28499990.pt +3 -0
  4. SoccerTwos/checkpoint.pt +1 -1
  5. SoccerTwos/events.out.tfevents.1725586939.Bretts-MBP.home.69888.0 +2 -2
  6. SoccerTwos/events.out.tfevents.1725587481.Bretts-MBP.home.79481.0 +3 -0
  7. SoccerTwos/events.out.tfevents.1725587524.Bretts-MBP.home.80316.0 +3 -0
  8. config.json +1 -1
  9. configuration.yaml +1 -1
  10. run_logs/Player-0.log +2 -2
  11. run_logs/timers.json +58 -252
  12. run_logs/training_status.json +8 -8
SoccerTwos.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a84f8c77d9bf83dff8645d18f53acef46456bd68362764dbe05896a6f2c5494
3
  size 2351062
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d4e7cb2c895a79cdfa2697800611382150d89b0823c1e03c11043ad5d45312
3
  size 2351062
SoccerTwos/SoccerTwos-28499990.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395ca4b074d49f2dfbf9eaa92e64d2b82368579b91d38f148327fbfcc2497271
3
+ size 2351062
SoccerTwos/SoccerTwos-28499990.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470c45807f4c88c6972135c7be937b9d45f2069ce097d315a46f9fe860fcadbb
3
+ size 36303154
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35ee5cb7fc948e749ffd83b68391fb37fae04811bd5253c1dfc907e794c68875
3
  size 36301318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e30d481bab34b7f1d5658a801988cfe30b130665f0c400206bb7f8a2283ac6
3
  size 36301318
SoccerTwos/events.out.tfevents.1725586939.Bretts-MBP.home.69888.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca7860fabbb2225dbcb3d80f74a99d9aa29fa88b80a1d78a8be48ca25fc9b951
3
- size 12412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f718a94e45fa4caceeae35a762ce88714889e10962274e03fed189dd4c19459
3
+ size 118636
SoccerTwos/events.out.tfevents.1725587481.Bretts-MBP.home.79481.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5347e5bf50eea8fae0588190515cd7cf578716a2c029f2729f7dcd837ceb60b9
3
+ size 1899
SoccerTwos/events.out.tfevents.1725587524.Bretts-MBP.home.80316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa962cc4eb9fdf57a3ecb371809b645281b930414e4ff9aeff0e429d51878e0
3
+ size 13612113
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 40960, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 0.5, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.5, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "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": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "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": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 0.5, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.5, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "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": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "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
@@ -4,7 +4,7 @@ behaviors:
4
  trainer_type: poca
5
  hyperparameters:
6
  batch_size: 40960
7
- buffer_size: 40960
8
  learning_rate: 0.0003
9
  beta: 0.01
10
  epsilon: 0.2
 
4
  trainer_type: poca
5
  hyperparameters:
6
  batch_size: 40960
7
+ buffer_size: 163840
8
  learning_rate: 0.0003
9
  beta: 0.01
10
  epsilon: 0.2
run_logs/Player-0.log CHANGED
@@ -10,7 +10,7 @@ NullGfxDevice:
10
  Renderer: Null Device
11
  Vendor: Unity Technologies
12
  Begin MonoManager ReloadAssembly
13
- - Completed reload, in 0.048 seconds
14
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
15
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,6 +35,6 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
35
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
36
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
37
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
38
- UnloadTime: 0.207000 ms
39
  Registered Communicator in Agent.
40
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
10
  Renderer: Null Device
11
  Vendor: Unity Technologies
12
  Begin MonoManager ReloadAssembly
13
+ - Completed reload, in 0.033 seconds
14
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
15
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
35
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
36
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
37
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
38
+ UnloadTime: 0.253459 ms
39
  Registered Communicator in Agent.
40
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
run_logs/timers.json CHANGED
@@ -1,202 +1,8 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SoccerTwos.Policy.Entropy.mean": {
5
- "value": 2.3104376792907715,
6
- "min": 2.302708387374878,
7
- "max": 2.3104376792907715,
8
- "count": 2
9
- },
10
- "SoccerTwos.Policy.Entropy.sum": {
11
- "value": 44064.66796875,
12
- "min": 44064.66796875,
13
- "max": 45096.2421875,
14
- "count": 2
15
- },
16
- "SoccerTwos.Environment.EpisodeLength.mean": {
17
- "value": 72.80882352941177,
18
- "min": 72.80882352941177,
19
- "max": 75.28070175438596,
20
- "count": 2
21
- },
22
- "SoccerTwos.Environment.EpisodeLength.sum": {
23
- "value": 19804.0,
24
- "min": 17164.0,
25
- "max": 19804.0,
26
- "count": 2
27
- },
28
- "SoccerTwos.Self-play.ELO.mean": {
29
- "value": 27.68951240330878,
30
- "min": 19.39607555575033,
31
- "max": 27.68951240330878,
32
- "count": 2
33
- },
34
- "SoccerTwos.Self-play.ELO.sum": {
35
- "value": 3765.7736868499937,
36
- "min": 2211.1526133555376,
37
- "max": 3765.7736868499937,
38
- "count": 2
39
- },
40
- "SoccerTwos.Step.mean": {
41
- "value": 15529895.0,
42
- "min": 15519910.0,
43
- "max": 15529895.0,
44
- "count": 2
45
- },
46
- "SoccerTwos.Step.sum": {
47
- "value": 15529895.0,
48
- "min": 15519910.0,
49
- "max": 15529895.0,
50
- "count": 2
51
- },
52
- "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
- "value": 0.02609466202557087,
54
- "min": -0.017733389511704445,
55
- "max": 0.02609466202557087,
56
- "count": 2
57
- },
58
- "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
- "value": 3.5749688148498535,
60
- "min": -1.9861396551132202,
61
- "max": 3.5749688148498535,
62
- "count": 2
63
- },
64
- "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
- "value": 0.027021300047636032,
66
- "min": -0.026986951008439064,
67
- "max": 0.027021300047636032,
68
- "count": 2
69
- },
70
- "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
- "value": 3.701918125152588,
72
- "min": -3.022538423538208,
73
- "max": 3.701918125152588,
74
- "count": 2
75
- },
76
- "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
77
- "value": 0.1250358372926712,
78
- "min": 0.12375549226999283,
79
- "max": 0.1250358372926712,
80
- "count": 2
81
- },
82
- "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
83
- "value": 17.12990951538086,
84
- "min": 13.860614776611328,
85
- "max": 17.12990951538086,
86
- "count": 2
87
- },
88
- "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
89
- "value": 0.12515737116336823,
90
- "min": 0.1239084005355835,
91
- "max": 0.12515737116336823,
92
- "count": 2
93
- },
94
- "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
95
- "value": 17.146560668945312,
96
- "min": 13.877740859985352,
97
- "max": 17.146560668945312,
98
- "count": 2
99
- },
100
- "SoccerTwos.Policy.RndBaselineEstimate.mean": {
101
- "value": 4.329185685492121e-05,
102
- "min": 2.0809267880395055e-05,
103
- "max": 4.329185685492121e-05,
104
- "count": 2
105
- },
106
- "SoccerTwos.Policy.RndBaselineEstimate.sum": {
107
- "value": 0.005930984392762184,
108
- "min": 0.002330638002604246,
109
- "max": 0.005930984392762184,
110
- "count": 2
111
- },
112
- "SoccerTwos.Policy.RndValueEstimate.mean": {
113
- "value": 4.492986772675067e-05,
114
- "min": 2.2152127712615766e-05,
115
- "max": 4.492986772675067e-05,
116
- "count": 2
117
- },
118
- "SoccerTwos.Policy.RndValueEstimate.sum": {
119
- "value": 0.006155391689389944,
120
- "min": 0.0024810382165014744,
121
- "max": 0.006155391689389944,
122
- "count": 2
123
- },
124
- "SoccerTwos.Environment.CumulativeReward.mean": {
125
- "value": 0.0,
126
- "min": 0.0,
127
- "max": 0.0,
128
- "count": 2
129
- },
130
- "SoccerTwos.Environment.CumulativeReward.sum": {
131
- "value": 0.0,
132
- "min": 0.0,
133
- "max": 0.0,
134
- "count": 2
135
- },
136
- "SoccerTwos.Policy.ExtrinsicReward.mean": {
137
- "value": 0.225265693925593,
138
- "min": -0.13291785653148377,
139
- "max": 0.225265693925593,
140
- "count": 2
141
- },
142
- "SoccerTwos.Policy.ExtrinsicReward.sum": {
143
- "value": 30.861400067806244,
144
- "min": -14.886799931526184,
145
- "max": 30.861400067806244,
146
- "count": 2
147
- },
148
- "SoccerTwos.Policy.CuriosityReward.mean": {
149
- "value": 0.0,
150
- "min": 0.0,
151
- "max": 0.0,
152
- "count": 2
153
- },
154
- "SoccerTwos.Policy.CuriosityReward.sum": {
155
- "value": 0.0,
156
- "min": 0.0,
157
- "max": 0.0,
158
- "count": 2
159
- },
160
- "SoccerTwos.Policy.RndReward.mean": {
161
- "value": 1.4620670220399113e-06,
162
- "min": 1.4620670220399113e-06,
163
- "max": 1.4965675764041668e-06,
164
- "count": 2
165
- },
166
- "SoccerTwos.Policy.RndReward.sum": {
167
- "value": 0.00020030318201946784,
168
- "min": 0.00016761556855726667,
169
- "max": 0.00020030318201946784,
170
- "count": 2
171
- },
172
- "SoccerTwos.Environment.GroupCumulativeReward.mean": {
173
- "value": 0.225265693925593,
174
- "min": -0.13291785653148377,
175
- "max": 0.225265693925593,
176
- "count": 2
177
- },
178
- "SoccerTwos.Environment.GroupCumulativeReward.sum": {
179
- "value": 30.861400067806244,
180
- "min": -14.886799931526184,
181
- "max": 30.861400067806244,
182
- "count": 2
183
- },
184
- "SoccerTwos.IsTraining.mean": {
185
- "value": 1.0,
186
- "min": 1.0,
187
- "max": 1.0,
188
- "count": 2
189
- },
190
- "SoccerTwos.IsTraining.sum": {
191
- "value": 1.0,
192
- "min": 1.0,
193
- "max": 1.0,
194
- "count": 2
195
- }
196
- },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
- "start_time_seconds": "1725586829",
200
  "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
201
  "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume",
202
  "mlagents_version": "1.1.0.dev0",
@@ -204,103 +10,103 @@
204
  "communication_protocol_version": "1.5.0",
205
  "pytorch_version": "2.4.0",
206
  "numpy_version": "1.23.5",
207
- "end_time_seconds": "1725586924"
208
  },
209
- "total": 95.26591454198933,
210
  "count": 1,
211
- "self": 10.003630083985627,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.017524958006106317,
215
  "count": 1,
216
- "self": 0.017524958006106317
217
  },
218
  "TrainerController.start_learning": {
219
- "total": 85.2447594999976,
220
  "count": 1,
221
- "self": 0.017233890888746828,
222
  "children": {
223
  "TrainerController._reset_env": {
224
- "total": 5.490196374972584,
225
  "count": 2,
226
- "self": 5.490196374972584
227
  },
228
  "TrainerController.advance": {
229
- "total": 79.61357340114773,
230
- "count": 1694,
231
- "self": 0.01448743074433878,
232
  "children": {
233
  "env_step": {
234
- "total": 74.1615375718684,
235
- "count": 1694,
236
- "self": 71.73426827054936,
237
  "children": {
238
  "SubprocessEnvManager._take_step": {
239
- "total": 2.4173300749680493,
240
- "count": 1694,
241
- "self": 0.08317474604700692,
242
  "children": {
243
  "TorchPolicy.evaluate": {
244
- "total": 2.3341553289210424,
245
- "count": 3140,
246
- "self": 2.3341553289210424
247
  }
248
  }
249
  },
250
  "workers": {
251
- "total": 0.00993922635097988,
252
- "count": 1693,
253
  "self": 0.0,
254
  "children": {
255
  "worker_root": {
256
- "total": 76.73182422068203,
257
- "count": 1693,
258
  "is_parallel": true,
259
- "self": 9.939680468814913,
260
  "children": {
261
  "steps_from_proto": {
262
- "total": 0.0028328340558800846,
263
  "count": 4,
264
  "is_parallel": true,
265
- "self": 0.00041175202932208776,
266
  "children": {
267
  "_process_rank_one_or_two_observation": {
268
- "total": 0.002421082026557997,
269
  "count": 16,
270
  "is_parallel": true,
271
- "self": 0.002421082026557997
272
  }
273
  }
274
  },
275
  "UnityEnvironment.step": {
276
- "total": 66.78931091781124,
277
- "count": 1693,
278
  "is_parallel": true,
279
- "self": 0.1735401972255204,
280
  "children": {
281
  "UnityEnvironment._generate_step_input": {
282
- "total": 1.2961137160018552,
283
- "count": 1693,
284
  "is_parallel": true,
285
- "self": 1.2961137160018552
286
  },
287
  "communicator.exchange": {
288
- "total": 63.202866761013865,
289
- "count": 1693,
290
  "is_parallel": true,
291
- "self": 63.202866761013865
292
  },
293
  "steps_from_proto": {
294
- "total": 2.1167902435699943,
295
- "count": 3386,
296
  "is_parallel": true,
297
- "self": 0.25891925499308854,
298
  "children": {
299
  "_process_rank_one_or_two_observation": {
300
- "total": 1.8578709885769058,
301
- "count": 13544,
302
  "is_parallel": true,
303
- "self": 1.8578709885769058
304
  }
305
  }
306
  }
@@ -313,33 +119,33 @@
313
  }
314
  },
315
  "trainer_advance": {
316
- "total": 5.437548398535,
317
- "count": 1693,
318
- "self": 0.33169878588523716,
319
  "children": {
320
  "process_trajectory": {
321
- "total": 5.105849612649763,
322
- "count": 1693,
323
- "self": 5.105849612649763
324
  }
325
  }
326
  }
327
  }
328
  },
329
  "trainer_threads": {
330
- "total": 8.750066626816988e-07,
331
  "count": 1,
332
- "self": 8.750066626816988e-07
333
  },
334
  "TrainerController._save_models": {
335
- "total": 0.1237549579818733,
336
  "count": 1,
337
- "self": 0.000638124969555065,
338
  "children": {
339
  "RLTrainer._checkpoint": {
340
- "total": 0.12311683301231824,
341
  "count": 1,
342
- "self": 0.12311683301231824
343
  }
344
  }
345
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1725587476",
6
  "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
7
  "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume",
8
  "mlagents_version": "1.1.0.dev0",
 
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.4.0",
12
  "numpy_version": "1.23.5",
13
+ "end_time_seconds": "1725587506"
14
  },
15
+ "total": 29.759251416980987,
16
  "count": 1,
17
+ "self": 0.05417570800636895,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.01983258398831822,
21
  "count": 1,
22
+ "self": 0.01983258398831822
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 29.6852431249863,
26
  "count": 1,
27
+ "self": 0.005499970284290612,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 5.607676666986663,
31
  "count": 2,
32
+ "self": 5.607676666986663
33
  },
34
  "TrainerController.advance": {
35
+ "total": 23.952345778699964,
36
+ "count": 544,
37
+ "self": 0.004761990217957646,
38
  "children": {
39
  "env_step": {
40
+ "total": 22.437635668349685,
41
+ "count": 544,
42
+ "self": 21.701109668210847,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
+ "total": 0.733093502552947,
46
+ "count": 544,
47
+ "self": 0.02726727639674209,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
+ "total": 0.7058262261562049,
51
+ "count": 988,
52
+ "self": 0.7058262261562049
53
  }
54
  }
55
  },
56
  "workers": {
57
+ "total": 0.0034324975858908147,
58
+ "count": 543,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
+ "total": 24.380553889030125,
63
+ "count": 543,
64
  "is_parallel": true,
65
+ "self": 3.3118312052392866,
66
  "children": {
67
  "steps_from_proto": {
68
+ "total": 0.0028238339873496443,
69
  "count": 4,
70
  "is_parallel": true,
71
+ "self": 0.0003903749748133123,
72
  "children": {
73
  "_process_rank_one_or_two_observation": {
74
+ "total": 0.002433459012536332,
75
  "count": 16,
76
  "is_parallel": true,
77
+ "self": 0.002433459012536332
78
  }
79
  }
80
  },
81
  "UnityEnvironment.step": {
82
+ "total": 21.06589884980349,
83
+ "count": 543,
84
  "is_parallel": true,
85
+ "self": 0.05391684197820723,
86
  "children": {
87
  "UnityEnvironment._generate_step_input": {
88
+ "total": 0.42568054268485866,
89
+ "count": 543,
90
  "is_parallel": true,
91
+ "self": 0.42568054268485866
92
  },
93
  "communicator.exchange": {
94
+ "total": 19.910471767303534,
95
+ "count": 543,
96
  "is_parallel": true,
97
+ "self": 19.910471767303534
98
  },
99
  "steps_from_proto": {
100
+ "total": 0.675829697836889,
101
+ "count": 1086,
102
  "is_parallel": true,
103
+ "self": 0.08203905361006036,
104
  "children": {
105
  "_process_rank_one_or_two_observation": {
106
+ "total": 0.5937906442268286,
107
+ "count": 4344,
108
  "is_parallel": true,
109
+ "self": 0.5937906442268286
110
  }
111
  }
112
  }
 
119
  }
120
  },
121
  "trainer_advance": {
122
+ "total": 1.5099481201323215,
123
+ "count": 543,
124
+ "self": 0.03519886895082891,
125
  "children": {
126
  "process_trajectory": {
127
+ "total": 1.4747492511814926,
128
+ "count": 543,
129
+ "self": 1.4747492511814926
130
  }
131
  }
132
  }
133
  }
134
  },
135
  "trainer_threads": {
136
+ "total": 5.420006345957518e-07,
137
  "count": 1,
138
+ "self": 5.420006345957518e-07
139
  },
140
  "TrainerController._save_models": {
141
+ "total": 0.11972016701474786,
142
  "count": 1,
143
+ "self": 0.000630917027592659,
144
  "children": {
145
  "RLTrainer._checkpoint": {
146
+ "total": 0.1190892499871552,
147
  "count": 1,
148
+ "self": 0.1190892499871552
149
  }
150
  }
151
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,24 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 39.4662628461065,
4
  "checkpoints": [
5
  {
6
- "steps": 15535538,
7
- "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-15535538.onnx",
8
  "reward": 0.0,
9
- "creation_time": 1725586914.6342201,
10
  "auxillary_file_paths": [
11
- "results/sept-run-01/SoccerTwos/SoccerTwos-15535538.pt"
12
  ]
13
  }
14
  ],
15
  "final_checkpoint": {
16
- "steps": 15535538,
17
  "file_path": "results/sept-run-01/SoccerTwos.onnx",
18
  "reward": 0.0,
19
- "creation_time": 1725586914.6342201,
20
  "auxillary_file_paths": [
21
- "results/sept-run-01/SoccerTwos/SoccerTwos-15535538.pt"
22
  ]
23
  }
24
  },
 
1
  {
2
  "SoccerTwos": {
3
+ "elo": 54.007814619269446,
4
  "checkpoints": [
5
  {
6
+ "steps": 15648774,
7
+ "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-15648774.onnx",
8
  "reward": 0.0,
9
+ "creation_time": 1725587506.053865,
10
  "auxillary_file_paths": [
11
+ "results/sept-run-01/SoccerTwos/SoccerTwos-15648774.pt"
12
  ]
13
  }
14
  ],
15
  "final_checkpoint": {
16
+ "steps": 15648774,
17
  "file_path": "results/sept-run-01/SoccerTwos.onnx",
18
  "reward": 0.0,
19
+ "creation_time": 1725587506.053865,
20
  "auxillary_file_paths": [
21
+ "results/sept-run-01/SoccerTwos/SoccerTwos-15648774.pt"
22
  ]
23
  }
24
  },