Harm commited on
Commit
4585609
1 Parent(s): ba50583

First Push`

Browse files
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - unity-ml-agents
5
+ - ml-agents
6
+ - deep-reinforcement-learning
7
+ - reinforcement-learning
8
+ - ML-Agents-SoccerTwos
9
+ library_name: ml-agents
10
+ ---
11
+
12
+ # **poca** Agent playing **SoccerTwos**
13
+ This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
14
+
15
+ ## Usage (with ML-Agents)
16
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+
19
+
20
+ ### Resume the training
21
+ ```
22
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
23
+ ```
24
+ ### Watch your Agent play
25
+ You can watch your agent **playing directly in your browser:**.
26
+
27
+ 1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
28
+ 2. Step 1: Write your model_id: Harm/poca-SoccerTwos-10M
29
+ 3. Step 2: Select your *.nn /*.onnx file
30
+ 4. Click on Watch the agent play 👀
31
+
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e03192c09e5b55a709174bd9cdce81c017116da4a59dd180b160b31cd86f68
3
+ size 1768746
SoccerTwos/SoccerTwos-3999362.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248e23754aee64f0c8f18b3c2333809f66787475f942c6c60cb9dc48505c8302
3
+ size 1768746
SoccerTwos/SoccerTwos-3999362.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7440f8e2662ecb2492dd9a818eb974475d63e290eccdc05966b379fabf0b0383
3
+ size 28429903
SoccerTwos/SoccerTwos-4499216.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e79aecdd652a0d120719a820a007a1d5ee49d23a32d4e90d51175115b8af7ed
3
+ size 1768746
SoccerTwos/SoccerTwos-4499216.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9465262362138095996e5e8db29453f91bac7b4bfec0fb272dc4d4ac22195f78
3
+ size 28429903
SoccerTwos/SoccerTwos-4999076.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0513624f1895b60164d6df7d2afb9d745ee6afb5d79b9bd684d8e9b63bca95bc
3
+ size 1768746
SoccerTwos/SoccerTwos-4999076.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a792cd38ffe87872265c615220b7e9f05a77951e0b7316af829d58576cf1c012
3
+ size 28429903
SoccerTwos/SoccerTwos-5499454.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfd05b59f1e5dc0475e87c4b460493e9350353d88407a3e9132d97acb96ce31
3
+ size 1768746
SoccerTwos/SoccerTwos-5499454.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fc605d4d5074b644902198e6fb35bade66c3e6e65d8d3553ef87bc486492cf1
3
+ size 28429903
SoccerTwos/SoccerTwos-5627454.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e03192c09e5b55a709174bd9cdce81c017116da4a59dd180b160b31cd86f68
3
+ size 1768746
SoccerTwos/SoccerTwos-5627454.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0b9978ab9cfe9257458d3602b6261d39cbbf79139a8be8952e00c5d647ae5b
3
+ size 28429903
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f36d0f8a6fc45795aefebb05c223a629ec6a81de41657d8033781a497021ac9
3
+ size 28428927
SoccerTwos/events.out.tfevents.1682599911.ZB-5CG0095CZ3.5988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51c1ab6c55cc8f0c298b94cd1bfcd3f8d6c41351c396117fbb0e97abb8ca563
3
+ size 1211570
config.json ADDED
@@ -0,0 +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": 100000000, "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-10M", "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 ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_settings: null
2
+ behaviors:
3
+ SoccerTwos:
4
+ trainer_type: poca
5
+ hyperparameters:
6
+ batch_size: 2048
7
+ buffer_size: 20480
8
+ learning_rate: 0.0003
9
+ beta: 0.005
10
+ epsilon: 0.2
11
+ lambd: 0.95
12
+ num_epoch: 3
13
+ learning_rate_schedule: constant
14
+ beta_schedule: constant
15
+ epsilon_schedule: constant
16
+ checkpoint_interval: 500000
17
+ network_settings:
18
+ normalize: false
19
+ hidden_units: 512
20
+ num_layers: 2
21
+ vis_encode_type: simple
22
+ memory: null
23
+ goal_conditioning_type: hyper
24
+ deterministic: false
25
+ reward_signals:
26
+ extrinsic:
27
+ gamma: 0.99
28
+ strength: 1.0
29
+ network_settings:
30
+ normalize: false
31
+ hidden_units: 128
32
+ num_layers: 2
33
+ vis_encode_type: simple
34
+ memory: null
35
+ goal_conditioning_type: hyper
36
+ deterministic: false
37
+ init_path: null
38
+ keep_checkpoints: 5
39
+ even_checkpoints: false
40
+ max_steps: 100000000
41
+ time_horizon: 1000
42
+ summary_freq: 10000
43
+ threaded: false
44
+ self_play:
45
+ save_steps: 50000
46
+ team_change: 200000
47
+ swap_steps: 2000
48
+ window: 10
49
+ play_against_latest_model_ratio: 0.5
50
+ initial_elo: 1200.0
51
+ behavioral_cloning: null
52
+ env_settings:
53
+ env_path: ./training-envs-executables/SoccerTwos.exe
54
+ env_args: null
55
+ base_port: 5005
56
+ num_envs: 1
57
+ num_areas: 1
58
+ seed: -1
59
+ max_lifetime_restarts: 10
60
+ restarts_rate_limit_n: 1
61
+ restarts_rate_limit_period_s: 60
62
+ engine_settings:
63
+ width: 84
64
+ height: 84
65
+ quality_level: 5
66
+ time_scale: 20
67
+ target_frame_rate: -1
68
+ capture_frame_rate: 60
69
+ no_graphics: true
70
+ environment_parameters: null
71
+ checkpoint_settings:
72
+ run_id: SoccerTwos-10M
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
80
+ torch_settings:
81
+ device: null
82
+ debug: false
run_logs/timers.json ADDED
@@ -0,0 +1,368 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.7530072927474976,
6
+ "min": 1.5153335332870483,
7
+ "max": 3.2957513332366943,
8
+ "count": 562
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 30684.638671875,
12
+ "min": 17372.4140625,
13
+ "max": 133188.890625,
14
+ "count": 562
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 999.0,
18
+ "min": 442.72727272727275,
19
+ "max": 999.0,
20
+ "count": 562
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19980.0,
24
+ "min": 14392.0,
25
+ "max": 26360.0,
26
+ "count": 562
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1199.8792716089524,
30
+ "min": 1191.3747873305135,
31
+ "max": 1199.8821415541559,
32
+ "count": 113
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 2399.758543217905,
36
+ "min": 2382.749574661027,
37
+ "max": 14394.102599354906,
38
+ "count": 113
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 5619454.0,
42
+ "min": 9200.0,
43
+ "max": 5619454.0,
44
+ "count": 562
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 5619454.0,
48
+ "min": 9200.0,
49
+ "max": 5619454.0,
50
+ "count": 562
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 3.6033758078701794e-05,
54
+ "min": -0.4588257670402527,
55
+ "max": 0.08562135696411133,
56
+ "count": 562
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.00036033758078701794,
60
+ "min": -4.588257789611816,
61
+ "max": 1.3699417114257812,
62
+ "count": 562
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 3.7475030694622546e-05,
66
+ "min": -0.37872445583343506,
67
+ "max": 0.0855926051735878,
68
+ "count": 562
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.00037475029239431024,
72
+ "min": -3.7872445583343506,
73
+ "max": 1.3694816827774048,
74
+ "count": 562
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 562
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 562
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.0,
90
+ "min": -0.5454545454545454,
91
+ "max": 0.32797332604726154,
92
+ "count": 562
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 0.0,
96
+ "min": -6.0,
97
+ "max": 4.919599890708923,
98
+ "count": 562
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.0,
102
+ "min": -0.5454545454545454,
103
+ "max": 0.32797332604726154,
104
+ "count": 562
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 0.0,
108
+ "min": -6.0,
109
+ "max": 4.919599890708923,
110
+ "count": 562
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 562
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 562
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.01523812247639095,
126
+ "min": 0.010124737523923007,
127
+ "max": 0.024689055467024445,
128
+ "count": 257
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.01523812247639095,
132
+ "min": 0.010124737523923007,
133
+ "max": 0.024689055467024445,
134
+ "count": 257
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 5.359651996291367e-09,
138
+ "min": 1.404278090107643e-09,
139
+ "max": 0.007951977666622648,
140
+ "count": 257
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 5.359651996291367e-09,
144
+ "min": 1.404278090107643e-09,
145
+ "max": 0.007951977666622648,
146
+ "count": 257
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 7.776809699914603e-09,
150
+ "min": 1.8967375151982917e-09,
151
+ "max": 0.009293046900226424,
152
+ "count": 257
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 7.776809699914603e-09,
156
+ "min": 1.8967375151982917e-09,
157
+ "max": 0.009293046900226424,
158
+ "count": 257
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 257
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 257
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 257
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 257
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 257
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 257
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1682599907",
200
+ "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
201
+ "command_line_arguments": "C:\\Users\\HBU1808.39421\\.conda\\envs\\hfrl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-10M --no-graphics",
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": "2.0.0+cpu",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1682626712"
208
+ },
209
+ "total": 26804.6690466,
210
+ "count": 1,
211
+ "self": 0.6840587999977288,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.13094649999999985,
215
+ "count": 1,
216
+ "self": 0.13094649999999985
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 26803.8540413,
220
+ "count": 1,
221
+ "self": 14.14166590019886,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 7.177210200002125,
225
+ "count": 28,
226
+ "self": 7.177210200002125
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 26782.188153699797,
230
+ "count": 365965,
231
+ "self": 14.75982709996606,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 11379.480486999546,
235
+ "count": 365965,
236
+ "self": 8785.837795099784,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 2584.2824252000487,
240
+ "count": 365965,
241
+ "self": 87.59324310027068,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 2496.689182099778,
245
+ "count": 726662,
246
+ "self": 2496.689182099778
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 9.36026669971396,
252
+ "count": 365964,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 26779.30251230026,
257
+ "count": 365964,
258
+ "is_parallel": true,
259
+ "self": 19725.317573300093,
260
+ "children": {
261
+ "steps_from_proto": {
262
+ "total": 0.09141170000155219,
263
+ "count": 56,
264
+ "is_parallel": true,
265
+ "self": 0.017937900010898566,
266
+ "children": {
267
+ "_process_rank_one_or_two_observation": {
268
+ "total": 0.07347379999065362,
269
+ "count": 224,
270
+ "is_parallel": true,
271
+ "self": 0.07347379999065362
272
+ }
273
+ }
274
+ },
275
+ "UnityEnvironment.step": {
276
+ "total": 7053.893527300164,
277
+ "count": 365964,
278
+ "is_parallel": true,
279
+ "self": 386.408833898543,
280
+ "children": {
281
+ "UnityEnvironment._generate_step_input": {
282
+ "total": 298.76427030093015,
283
+ "count": 365964,
284
+ "is_parallel": true,
285
+ "self": 298.76427030093015
286
+ },
287
+ "communicator.exchange": {
288
+ "total": 5092.0302624005535,
289
+ "count": 365964,
290
+ "is_parallel": true,
291
+ "self": 5092.0302624005535
292
+ },
293
+ "steps_from_proto": {
294
+ "total": 1276.6901607001375,
295
+ "count": 731928,
296
+ "is_parallel": true,
297
+ "self": 244.83094719978112,
298
+ "children": {
299
+ "_process_rank_one_or_two_observation": {
300
+ "total": 1031.8592135003564,
301
+ "count": 2927712,
302
+ "is_parallel": true,
303
+ "self": 1031.8592135003564
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ },
315
+ "trainer_advance": {
316
+ "total": 15387.947839600287,
317
+ "count": 365964,
318
+ "self": 96.26984210020419,
319
+ "children": {
320
+ "process_trajectory": {
321
+ "total": 2154.12127770009,
322
+ "count": 365964,
323
+ "self": 2150.8659975000855,
324
+ "children": {
325
+ "RLTrainer._checkpoint": {
326
+ "total": 3.255280200004563,
327
+ "count": 11,
328
+ "self": 3.255280200004563
329
+ }
330
+ }
331
+ },
332
+ "_update_policy": {
333
+ "total": 13137.556719799994,
334
+ "count": 258,
335
+ "self": 1280.481288900055,
336
+ "children": {
337
+ "TorchPOCAOptimizer.update": {
338
+ "total": 11857.075430899939,
339
+ "count": 7740,
340
+ "self": 11857.075430899939
341
+ }
342
+ }
343
+ }
344
+ }
345
+ }
346
+ }
347
+ },
348
+ "trainer_threads": {
349
+ "total": 2.8000031306874007e-06,
350
+ "count": 1,
351
+ "self": 2.8000031306874007e-06
352
+ },
353
+ "TrainerController._save_models": {
354
+ "total": 0.3470086999986961,
355
+ "count": 1,
356
+ "self": 0.007350699997914489,
357
+ "children": {
358
+ "RLTrainer._checkpoint": {
359
+ "total": 0.3396580000007816,
360
+ "count": 1,
361
+ "self": 0.3396580000007816
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SoccerTwos": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 3999362,
6
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-3999362.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1682618144.0289497,
9
+ "auxillary_file_paths": [
10
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-3999362.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 4499216,
15
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4499216.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1682620396.255104,
18
+ "auxillary_file_paths": [
19
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4499216.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 4999076,
24
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4999076.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1682622663.9818969,
27
+ "auxillary_file_paths": [
28
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-4999076.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 5499454,
33
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5499454.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1682625923.34515,
36
+ "auxillary_file_paths": [
37
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5499454.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 5627454,
42
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1682626711.4336407,
45
+ "auxillary_file_paths": [
46
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1200.1285520530978,
51
+ "final_checkpoint": {
52
+ "steps": 5627454,
53
+ "file_path": "results\\SoccerTwos-10M\\SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1682626711.4336407,
56
+ "auxillary_file_paths": [
57
+ "results\\SoccerTwos-10M\\SoccerTwos\\SoccerTwos-5627454.pt"
58
+ ]
59
+ }
60
+ },
61
+ "metadata": {
62
+ "stats_format_version": "0.3.0",
63
+ "mlagents_version": "0.31.0.dev0",
64
+ "torch_version": "2.0.0+cpu"
65
+ }
66
+ }