Hugging Face's logo

shubhamagarwal92
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
shubhamagarwal92 commited on
Commit
f24c659
•
1 Parent(s): 4c77d0d

First Push

Browse files
Files changed (18) hide show
  1. SoccerTwos.onnx +3 -0
  2. SoccerTwos/SoccerTwos-48499886.onnx +3 -0
  3. SoccerTwos/SoccerTwos-48499886.pt +3 -0
  4. SoccerTwos/SoccerTwos-48999658.onnx +3 -0
  5. SoccerTwos/SoccerTwos-48999658.pt +3 -0
  6. SoccerTwos/SoccerTwos-49499830.onnx +3 -0
  7. SoccerTwos/SoccerTwos-49499830.pt +3 -0
  8. SoccerTwos/SoccerTwos-49999888.onnx +3 -0
  9. SoccerTwos/SoccerTwos-49999888.pt +3 -0
  10. SoccerTwos/SoccerTwos-50000188.onnx +3 -0
  11. SoccerTwos/SoccerTwos-50000188.pt +3 -0
  12. SoccerTwos/checkpoint.pt +3 -0
  13. SoccerTwos/events.out.tfevents.1691503210.u116570.335152.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +0 -0
  17. run_logs/timers.json +396 -14
  18. run_logs/training_status.json +58 -2
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb54278d9c230bfbcd5145ba3e1938b26a592f5bbd3c426af4d07ba01ceaba3e
3
+ size 1764633
SoccerTwos/SoccerTwos-48499886.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02b34816f8cc964a6edec892d5ae99c53cb1edbf5d474a8415650e3d0d118ae
3
+ size 1764633
SoccerTwos/SoccerTwos-48499886.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e49dfaa8116cd2c9dc39e80ba714b1f796e6d228742ca14920fb3045f23b885
3
+ size 28421201
SoccerTwos/SoccerTwos-48999658.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dc3f58fc59f7f38a68ba4d1d776d67588b386c4091c326f430c53f5be22daf
3
+ size 1764633
SoccerTwos/SoccerTwos-48999658.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4590c29ef7f3c16b0b9650882c33a6a34d3dc5e54d56ed8c5856639027e4d5d
3
+ size 28421201
SoccerTwos/SoccerTwos-49499830.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921038ce608f8fa453e5ea392c397bd4b4f5a6124b1270a9b9e91c2e6a8a6721
3
+ size 1764633
SoccerTwos/SoccerTwos-49499830.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c6efbe527b1b15178dbf78b847c48e1534161ba0dc93f0c968ab91be68f238
3
+ size 28421201
SoccerTwos/SoccerTwos-49999888.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb54278d9c230bfbcd5145ba3e1938b26a592f5bbd3c426af4d07ba01ceaba3e
3
+ size 1764633
SoccerTwos/SoccerTwos-49999888.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9caa4506291b2c633b183ebbb0f78c3d0e564cc8a109d52c87e1c23d91007ae
3
+ size 28421201
SoccerTwos/SoccerTwos-50000188.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb54278d9c230bfbcd5145ba3e1938b26a592f5bbd3c426af4d07ba01ceaba3e
3
+ size 1764633
SoccerTwos/SoccerTwos-50000188.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe179c35d5bd71b5f419f678cd9fdcd0e96c669318c9de5b9cde560f411d047
3
+ size 28421201
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe179c35d5bd71b5f419f678cd9fdcd0e96c669318c9de5b9cde560f411d047
3
+ size 28421201
SoccerTwos/events.out.tfevents.1691503210.u116570.335152.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc838d60c49f7a30e4b3cf0d5ed66d4ff5074377412b3df3a7b77e8c9a669095
3
+ size 16743065
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.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": 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.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -73,7 +73,7 @@ checkpoint_settings:
73
  initialize_from: null
74
  load_model: false
75
  resume: false
76
- force: false
77
  train_model: false
78
  inference: false
79
  results_dir: results
 
73
  initialize_from: null
74
  load_model: false
75
  resume: false
76
+ force: true
77
  train_model: false
78
  inference: false
79
  results_dir: results
run_logs/Player-0.log CHANGED
The diff for this file is too large to render. See raw diff
 
run_logs/timers.json CHANGED
@@ -1,40 +1,422 @@
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
- "start_time_seconds": "1691500662",
6
  "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]",
7
- "command_line_arguments": "/home/shubham/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
8
  "mlagents_version": "0.31.0.dev0",
9
  "mlagents_envs_version": "0.31.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
- "pytorch_version": "1.11.0+cu102",
12
  "numpy_version": "1.21.2",
13
- "end_time_seconds": "1691500663"
14
  },
15
- "total": 0.7404054794460535,
16
  "count": 1,
17
- "self": 0.21871372498571873,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.007452774792909622,
21
  "count": 1,
22
- "self": 0.007452774792909622
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 0.5142389796674252,
26
  "count": 1,
27
- "self": 5.456991493701935e-05,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 0.514059130102396,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "count": 1,
32
- "self": 0.514059130102396
33
  },
34
  "TrainerController._save_models": {
35
- "total": 0.00012527965009212494,
36
  "count": 1,
37
- "self": 0.00012527965009212494
 
 
 
 
 
 
 
38
  }
39
  }
40
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.88508939743042,
6
+ "min": 0.32007288932800293,
7
+ "max": 3.295736312866211,
8
+ "count": 5000
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 38365.33984375,
12
+ "min": 3157.25439453125,
13
+ "max": 135342.46875,
14
+ "count": 5000
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 93.16981132075472,
18
+ "min": 66.58333333333333,
19
+ "max": 999.0,
20
+ "count": 5000
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19752.0,
24
+ "min": 14780.0,
25
+ "max": 25008.0,
26
+ "count": 5000
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1512.427935707163,
30
+ "min": 1170.3451905441245,
31
+ "max": 1525.702528180523,
32
+ "count": 1457
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 160317.36118495927,
36
+ "min": 2340.9549261537477,
37
+ "max": 226001.99945326115,
38
+ "count": 1457
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 49999888.0,
42
+ "min": 9520.0,
43
+ "max": 49999888.0,
44
+ "count": 5000
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 49999888.0,
48
+ "min": 9520.0,
49
+ "max": 49999888.0,
50
+ "count": 5000
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.021812312304973602,
54
+ "min": -0.13352897763252258,
55
+ "max": 0.08573879301548004,
56
+ "count": 5000
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 2.312105178833008,
60
+ "min": -13.512857437133789,
61
+ "max": 8.831095695495605,
62
+ "count": 5000
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.020299047231674194,
66
+ "min": -0.1314021795988083,
67
+ "max": 0.0843314379453659,
68
+ "count": 5000
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 2.1516990661621094,
72
+ "min": -13.528635025024414,
73
+ "max": 8.686138153076172,
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": -0.14448867991285505,
90
+ "min": -0.7333333333333333,
91
+ "max": 0.4688516100568156,
92
+ "count": 5000
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -15.315800070762634,
96
+ "min": -45.10600012540817,
97
+ "max": 41.33040010929108,
98
+ "count": 5000
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.14448867991285505,
102
+ "min": -0.7333333333333333,
103
+ "max": 0.4688516100568156,
104
+ "count": 5000
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -15.315800070762634,
108
+ "min": -45.10600012540817,
109
+ "max": 41.33040010929108,
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": 0.01772666120547607,
126
+ "min": 0.010309555162287628,
127
+ "max": 0.02550357847746151,
128
+ "count": 2317
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01772666120547607,
132
+ "min": 0.010309555162287628,
133
+ "max": 0.02550357847746151,
134
+ "count": 2317
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.07129886721571287,
138
+ "min": 1.7289252079334452e-13,
139
+ "max": 0.08477772573630014,
140
+ "count": 2317
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.07129886721571287,
144
+ "min": 1.7289252079334452e-13,
145
+ "max": 0.08477772573630014,
146
+ "count": 2317
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.07237084607283274,
150
+ "min": 1.806328044271103e-13,
151
+ "max": 0.0861017644405365,
152
+ "count": 2317
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.07237084607283274,
156
+ "min": 1.806328044271103e-13,
157
+ "max": 0.0861017644405365,
158
+ "count": 2317
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2317
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2317
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 2317
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 2317
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 2317
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 2317
195
+ }
196
+ },
197
  "metadata": {
198
  "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1691503209",
200
  "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]",
201
+ "command_line_arguments": "/home/shubham/anaconda3/envs/rl_7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
202
  "mlagents_version": "0.31.0.dev0",
203
  "mlagents_envs_version": "0.31.0.dev0",
204
  "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "1.11.0",
206
  "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1691594759"
208
  },
209
+ "total": 91550.12136934884,
210
  "count": 1,
211
+ "self": 0.21866557747125626,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.007789118215441704,
215
  "count": 1,
216
+ "self": 0.007789118215441704
217
  },
218
  "TrainerController.start_learning": {
219
+ "total": 91549.89491465315,
220
  "count": 1,
221
+ "self": 34.558459451422095,
222
  "children": {
223
  "TrainerController._reset_env": {
224
+ "total": 15.585894523188472,
225
+ "count": 249,
226
+ "self": 15.585894523188472
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 91499.61708582379,
230
+ "count": 3267196,
231
+ "self": 32.871663462370634,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 50005.42744296044,
235
+ "count": 3267196,
236
+ "self": 44438.527459194884,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 5545.596074255183,
240
+ "count": 3267196,
241
+ "self": 237.7563860118389,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 5307.839688243344,
245
+ "count": 6432068,
246
+ "self": 5307.839688243344
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 21.30390951037407,
252
+ "count": 3267196,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 91468.98101312853,
257
+ "count": 3267196,
258
+ "is_parallel": true,
259
+ "self": 52545.723739005625,
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": 0.003239186480641365,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0005889143794775009,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.002650272101163864,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.002650272101163864
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.022952860221266747,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0008996389806270599,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0006436463445425034,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0006436463445425034
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.01872406341135502,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.01872406341135502
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0026855114847421646,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00039279647171497345,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.002292715013027191,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.002292715013027191
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 38922.63351684064,
319
+ "count": 3267195,
320
+ "is_parallel": true,
321
+ "self": 2651.4995847065,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 1685.1483978647739,
325
+ "count": 3267195,
326
+ "is_parallel": true,
327
+ "self": 1685.1483978647739
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 26989.567140348256,
331
+ "count": 3267195,
332
+ "is_parallel": true,
333
+ "self": 26989.567140348256
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 7596.418393921107,
337
+ "count": 6534390,
338
+ "is_parallel": true,
339
+ "self": 1098.265936370939,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 6498.152457550168,
343
+ "count": 26137560,
344
+ "is_parallel": true,
345
+ "self": 6498.152457550168
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.6237572822719812,
353
+ "count": 496,
354
+ "is_parallel": true,
355
+ "self": 0.0929538756608963,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.5308034066110849,
359
+ "count": 1984,
360
+ "is_parallel": true,
361
+ "self": 0.5308034066110849
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 41461.31797940098,
373
+ "count": 3267196,
374
+ "self": 387.35703905671835,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 5851.3373470995575,
378
+ "count": 3267196,
379
+ "self": 5838.157907405868,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 13.179439693689346,
383
+ "count": 100,
384
+ "self": 13.179439693689346
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 35222.6235932447,
390
+ "count": 2317,
391
+ "self": 5723.476034210995,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 29499.147559033707,
395
+ "count": 69510,
396
+ "self": 29499.147559033707
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 5.699694156646729e-07,
406
  "count": 1,
407
+ "self": 5.699694156646729e-07
408
  },
409
  "TrainerController._save_models": {
410
+ "total": 0.13347428478300571,
411
  "count": 1,
412
+ "self": 0.0008611921221017838,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.13261309266090393,
416
+ "count": 1,
417
+ "self": 0.13261309266090393
418
+ }
419
+ }
420
  }
421
  }
422
  }
run_logs/training_status.json CHANGED
@@ -1,10 +1,66 @@
1
  {
2
  "SoccerTwos": {
3
- "elo": 1200.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  },
5
  "metadata": {
6
  "stats_format_version": "0.3.0",
7
  "mlagents_version": "0.31.0.dev0",
8
- "torch_version": "1.11.0+cu102"
9
  }
10
  }
 
1
  {
2
  "SoccerTwos": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 48499886,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499886.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1691591956.4555233,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48499886.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 48999658,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999658.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1691592890.2769072,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48999658.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 49499830,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499830.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1691593823.1330836,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49499830.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 49999888,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999888.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1691594759.338708,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49999888.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 50000188,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000188.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1691594759.5087287,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000188.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1508.2266078653274,
51
+ "final_checkpoint": {
52
+ "steps": 50000188,
53
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1691594759.5087287,
56
+ "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000188.pt"
58
+ ]
59
+ }
60
  },
61
  "metadata": {
62
  "stats_format_version": "0.3.0",
63
  "mlagents_version": "0.31.0.dev0",
64
+ "torch_version": "1.11.0"
65
  }
66
  }