Hugging Face's logo

yechenzhi1
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
yechenzhi1 commited on
Commit
7162d2d
•
1 Parent(s): 50a8af9

First Push

Browse files
Files changed (17) hide show
  1. SoccerTwos.onnx +3 -0
  2. SoccerTwos/SoccerTwos-48499652.onnx +3 -0
  3. SoccerTwos/SoccerTwos-48499652.pt +3 -0
  4. SoccerTwos/SoccerTwos-48999344.onnx +3 -0
  5. SoccerTwos/SoccerTwos-48999344.pt +3 -0
  6. SoccerTwos/SoccerTwos-49499882.onnx +3 -0
  7. SoccerTwos/SoccerTwos-49499882.pt +3 -0
  8. SoccerTwos/SoccerTwos-49999574.onnx +3 -0
  9. SoccerTwos/SoccerTwos-49999574.pt +3 -0
  10. SoccerTwos/SoccerTwos-50000574.onnx +3 -0
  11. SoccerTwos/SoccerTwos-50000574.pt +3 -0
  12. SoccerTwos/checkpoint.pt +1 -1
  13. SoccerTwos/events.out.tfevents.1709392019.kml-dtmachine-6629-prod.7065.0 +2 -2
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/timers.json +424 -0
  17. run_logs/training_status.json +66 -0
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bf8106a64b21509130a847d1193748f38c7364d0a9cadc3645c502ff4ccb22
3
+ size 1768747
SoccerTwos/SoccerTwos-48499652.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c4f8688755295e64de13b5a7e9ba948603624758ed95c92fd8ea765c19f65a
3
+ size 1768747
SoccerTwos/SoccerTwos-48499652.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7942bc6fa0243561fbb067827785e4a97c78fa9aab7b8f1b754ebb6ede3814b3
3
+ size 28430482
SoccerTwos/SoccerTwos-48999344.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab2be809c10ed136a1a464b9240a8735a6d8970a7468ecd0aaec4eb292a8b37
3
+ size 1768747
SoccerTwos/SoccerTwos-48999344.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd570f925ae2ad4974220a338443aa453af32e3f12b0eed35712c57b5faa83a
3
+ size 28430482
SoccerTwos/SoccerTwos-49499882.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75461d4307f58920792dfd63e9dc470200187ca0b085b9baf6e0c7225861581c
3
+ size 1768747
SoccerTwos/SoccerTwos-49499882.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6fc1e401b7d9cf9edc0d5d62d691b1a6b7d8b52db47f521c03d98cf09dae9b
3
+ size 28430482
SoccerTwos/SoccerTwos-49999574.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bf8106a64b21509130a847d1193748f38c7364d0a9cadc3645c502ff4ccb22
3
+ size 1768747
SoccerTwos/SoccerTwos-49999574.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe692f88c96591d7840194affc5ca169850751e26e5276f9c03301ae48588c3
3
+ size 28430482
SoccerTwos/SoccerTwos-50000574.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bf8106a64b21509130a847d1193748f38c7364d0a9cadc3645c502ff4ccb22
3
+ size 1768747
SoccerTwos/SoccerTwos-50000574.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb33b61befee2a17fa43876b427de3a1f7ae1ea7dac9726ff87ca97e8c923ad
3
+ size 28430482
SoccerTwos/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edbf055f444344a19f53855a66077f357af63739f61db4bfbd50464e32773de9
3
  size 28429366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1836ff6ef7a9b9646750157de377f98df9164f89d27cc9ddf9b655b9a7a520
3
  size 28429366
SoccerTwos/events.out.tfevents.1709392019.kml-dtmachine-6629-prod.7065.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2baf3c830c97e02f027f42559dd0df26bfa16d11f4b0ffd8d1d609c2299dfb39
3
- size 3828719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7786e6e5fd749f858b2a2a51caddca355f093e54e0ecbc04c769cbdb83cb6761
3
+ size 6735048
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/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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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": 0.0003, "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/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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos2", "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
@@ -71,7 +71,7 @@ engine_settings:
71
  no_graphics_monitor: false
72
  environment_parameters: null
73
  checkpoint_settings:
74
- run_id: SoccerTwos
75
  initialize_from: null
76
  load_model: false
77
  resume: false
 
71
  no_graphics_monitor: false
72
  environment_parameters: null
73
  checkpoint_settings:
74
+ run_id: SoccerTwos2
75
  initialize_from: null
76
  load_model: false
77
  resume: false
run_logs/timers.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.4303474426269531,
6
+ "min": 1.1953974962234497,
7
+ "max": 3.29569411277771,
8
+ "count": 5000
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 19132.328125,
12
+ "min": 16187.94921875,
13
+ "max": 143469.59375,
14
+ "count": 5000
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 999.0,
18
+ "min": 283.05263157894734,
19
+ "max": 999.0,
20
+ "count": 5000
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19980.0,
24
+ "min": 16156.0,
25
+ "max": 23956.0,
26
+ "count": 5000
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1204.4411450126954,
30
+ "min": 1189.2658214645403,
31
+ "max": 1221.1020871596347,
32
+ "count": 348
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 2408.882290025391,
36
+ "min": 2378.5316429290806,
37
+ "max": 38542.76393313485,
38
+ "count": 348
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 49999574.0,
42
+ "min": 9232.0,
43
+ "max": 49999574.0,
44
+ "count": 5000
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 49999574.0,
48
+ "min": 9232.0,
49
+ "max": 49999574.0,
50
+ "count": 5000
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 8.863906987244263e-05,
54
+ "min": -0.09684797376394272,
55
+ "max": 0.039017047733068466,
56
+ "count": 5000
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.0008863906841725111,
60
+ "min": -1.4526851177215576,
61
+ "max": 0.39017048478126526,
62
+ "count": 5000
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 8.832582534523681e-05,
66
+ "min": -0.09686007350683212,
67
+ "max": 0.03836328908801079,
68
+ "count": 5000
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.0008832582389004529,
72
+ "min": -1.4529011249542236,
73
+ "max": 0.3836328983306885,
74
+ "count": 5000
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 5000
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 5000
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.0,
90
+ "min": -0.6857384592294693,
91
+ "max": 0.30922666390736897,
92
+ "count": 5000
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 0.0,
96
+ "min": -17.829199939966202,
97
+ "max": 7.01119989156723,
98
+ "count": 5000
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.0,
102
+ "min": -0.6857384592294693,
103
+ "max": 0.30922666390736897,
104
+ "count": 5000
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 0.0,
108
+ "min": -17.829199939966202,
109
+ "max": 7.01119989156723,
110
+ "count": 5000
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 5000
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 5000
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.019303698907606304,
126
+ "min": 0.009621734620789841,
127
+ "max": 0.025912615560810082,
128
+ "count": 2287
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.019303698907606304,
132
+ "min": 0.009621734620789841,
133
+ "max": 0.025912615560810082,
134
+ "count": 2287
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 1.3651335052193106e-07,
138
+ "min": 7.843297929535642e-12,
139
+ "max": 0.017249827086925507,
140
+ "count": 2287
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 1.3651335052193106e-07,
144
+ "min": 7.843297929535642e-12,
145
+ "max": 0.017249827086925507,
146
+ "count": 2287
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 1.364581883098644e-07,
150
+ "min": 1.3570412126194068e-11,
151
+ "max": 0.01751269195228815,
152
+ "count": 2287
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 1.364581883098644e-07,
156
+ "min": 1.3570412126194068e-11,
157
+ "max": 0.01751269195228815,
158
+ "count": 2287
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2287
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2287
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.2,
175
+ "max": 0.20000000000000007,
176
+ "count": 2287
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.2,
181
+ "max": 0.20000000000000007,
182
+ "count": 2287
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005,
187
+ "max": 0.005000000000000001,
188
+ "count": 2287
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005,
193
+ "max": 0.005000000000000001,
194
+ "count": 2287
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1709392019",
200
+ "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
201
+ "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos2 --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": "2.2.1+cu121",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1709509854"
208
+ },
209
+ "total": 117835.85971496999,
210
+ "count": 1,
211
+ "self": 0.4010079428553581,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.04044067859649658,
215
+ "count": 1,
216
+ "self": 0.04044067859649658
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 117835.41826634854,
220
+ "count": 1,
221
+ "self": 49.42197136580944,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 24.56546761840582,
225
+ "count": 249,
226
+ "self": 24.56546761840582
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 117761.21391058713,
230
+ "count": 3252957,
231
+ "self": 53.66396142542362,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 55676.000531986356,
235
+ "count": 3252957,
236
+ "self": 43812.915923289955,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 11831.879136480391,
240
+ "count": 3252957,
241
+ "self": 426.82750248908997,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 11405.051633991301,
245
+ "count": 6462430,
246
+ "self": 11405.051633991301
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 31.205472216010094,
252
+ "count": 3252957,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 117734.94591672719,
257
+ "count": 3252957,
258
+ "is_parallel": true,
259
+ "self": 81630.8699169308,
260
+ "children": {
261
+ "run_training.setup": {
262
+ "total": 0.0,
263
+ "count": 0,
264
+ "is_parallel": true,
265
+ "self": 0.0,
266
+ "children": {
267
+ "steps_from_proto": {
268
+ "total": 0.0027211830019950867,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.000684984028339386,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0020361989736557007,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0020361989736557007
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.02486460655927658,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0005846098065376282,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.00047321617603302,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.00047321617603302
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.021958790719509125,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.021958790719509125
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0018479898571968079,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.0003945678472518921,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0014534220099449158,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0014534220099449158
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 36103.5907208547,
319
+ "count": 3252956,
320
+ "is_parallel": true,
321
+ "self": 1735.802337884903,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 1249.075766555965,
325
+ "count": 3252956,
326
+ "is_parallel": true,
327
+ "self": 1249.075766555965
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 27656.65300156176,
331
+ "count": 3252956,
332
+ "is_parallel": true,
333
+ "self": 27656.65300156176
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 5462.059614852071,
337
+ "count": 6505912,
338
+ "is_parallel": true,
339
+ "self": 1043.9579699635506,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 4418.10164488852,
343
+ "count": 26023648,
344
+ "is_parallel": true,
345
+ "self": 4418.10164488852
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.4852789416909218,
353
+ "count": 496,
354
+ "is_parallel": true,
355
+ "self": 0.09975766390562057,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.3855212777853012,
359
+ "count": 1984,
360
+ "is_parallel": true,
361
+ "self": 0.3855212777853012
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 62031.54941717535,
373
+ "count": 3252957,
374
+ "self": 635.0691465362906,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 6193.857440367341,
378
+ "count": 3252957,
379
+ "self": 6172.539449818432,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 21.31799054890871,
383
+ "count": 100,
384
+ "self": 21.31799054890871
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 55202.62283027172,
390
+ "count": 2287,
391
+ "self": 6496.640734091401,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 48705.98209618032,
395
+ "count": 68613,
396
+ "self": 48705.98209618032
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 1.3634562492370605e-06,
406
+ "count": 1,
407
+ "self": 1.3634562492370605e-06
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.21691541373729706,
411
+ "count": 1,
412
+ "self": 0.009875722229480743,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.20703969150781631,
416
+ "count": 1,
417
+ "self": 0.20703969150781631
418
+ }
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SoccerTwos": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 48499652,
6
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-48499652.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1709504964.3024058,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-48499652.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 48999344,
15
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-48999344.onnx",
16
+ "reward": null,
17
+ "creation_time": 1709506948.9082077,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-48999344.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 49499882,
24
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-49499882.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1709508576.0105872,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-49499882.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 49999574,
33
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-49999574.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1709509854.1974142,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-49999574.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 50000574,
42
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-50000574.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1709509854.5231159,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-50000574.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1204.4411450126954,
51
+ "final_checkpoint": {
52
+ "steps": 50000574,
53
+ "file_path": "results/SoccerTwos2/SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1709509854.5231159,
56
+ "auxillary_file_paths": [
57
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-50000574.pt"
58
+ ]
59
+ }
60
+ },
61
+ "metadata": {
62
+ "stats_format_version": "0.3.0",
63
+ "mlagents_version": "1.1.0.dev0",
64
+ "torch_version": "2.2.1+cu121"
65
+ }
66
+ }