c-wang commited on
Commit
d27150f
1 Parent(s): e17046d

First Push`

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: ml-agents
3
+ tags:
4
+ - SoccerTwos
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - ML-Agents-SoccerTwos
8
+ ---
9
+
10
+ # **poca** Agent playing **SoccerTwos**
11
+ This is a trained model of a **poca** agent playing **SoccerTwos**
12
+ using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
+
14
+ ## Usage (with ML-Agents)
15
+ The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
16
+
17
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
18
+ - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
19
+ browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
20
+ - A *longer tutorial* to understand how works ML-Agents:
21
+ https://huggingface.co/learn/deep-rl-course/unit5/introduction
22
+
23
+ ### Resume the training
24
+ ```bash
25
+ mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
26
+ ```
27
+
28
+ ### Watch your Agent play
29
+ You can watch your agent **playing directly in your browser**
30
+
31
+ 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
32
+ 2. Step 1: Find your model_id: c-wang/poca-SoccerTwos
33
+ 3. Step 2: Select your *.nn /*.onnx file
34
+ 4. Click on Watch the agent play 👀
35
+
SoccerTwos.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f321450ad9481edaf7f87f4716c8ccada6e005ab01fc9fc97ab6fd138b6640fc
3
+ size 1768747
SoccerTwos/SoccerTwos-48499860.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04f058401f8501090dc3b95eb31ab59a1645396ca09f49511fb43e749df278b
3
+ size 1768747
SoccerTwos/SoccerTwos-48499860.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413a0ff8e42509d47f2badebeec0a4517f9a3ea5c8e85d67ff1f5653568bc8c2
3
+ size 28430482
SoccerTwos/SoccerTwos-48999946.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aaf2d9235e221b84863575e87ec14a022f9e1bb504217581aaa1372630a3efc
3
+ size 1768747
SoccerTwos/SoccerTwos-48999946.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cee7956ce580832f6ba70c4f6e81af49829dd291c8a3843dc25e970c084cf81
3
+ size 28430482
SoccerTwos/SoccerTwos-49499990.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3182ef97e5b67a2227bb0681e09aabf86f8313c94558ba0661cafa64e69a2951
3
+ size 1768747
SoccerTwos/SoccerTwos-49499990.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06c2eab20d0bf857fba94021311988ee152187f4c0424f43b3a2f2bee636536
3
+ size 28430482
SoccerTwos/SoccerTwos-49999865.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f321450ad9481edaf7f87f4716c8ccada6e005ab01fc9fc97ab6fd138b6640fc
3
+ size 1768747
SoccerTwos/SoccerTwos-49999865.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560755c0c8edcbba87363929d19efe0d2bc703caec8d4163341caaa548c3aaf5
3
+ size 28430482
SoccerTwos/SoccerTwos-50000036.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f321450ad9481edaf7f87f4716c8ccada6e005ab01fc9fc97ab6fd138b6640fc
3
+ size 1768747
SoccerTwos/SoccerTwos-50000036.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b40232a13bd6ee815f27bc9c36949ea019ebfb779bb8fb6492b87b5a049fe
3
+ size 28430482
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0548f096aa212ec3fd3a159569beb8a6d425e10e70e642218a415161da955e69
3
+ size 28429366
SoccerTwos/events.out.tfevents.1703464607.DESKTOP-8RQVDLC.17120.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb40c5d2c351e8c256dbb6f47f022aa3ab2faff369f809eeb3c725c521069a64
3
+ size 27741948
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": 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.exe", "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 50000000
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/SoccerTwos.exe
54
+ env_args: null
55
+ base_port: 5005
56
+ num_envs: 1
57
+ num_areas: 1
58
+ timeout_wait: 60
59
+ seed: -1
60
+ max_lifetime_restarts: 10
61
+ restarts_rate_limit_n: 1
62
+ restarts_rate_limit_period_s: 60
63
+ engine_settings:
64
+ width: 84
65
+ height: 84
66
+ quality_level: 5
67
+ time_scale: 20
68
+ target_frame_rate: -1
69
+ capture_frame_rate: 60
70
+ no_graphics: true
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
78
+ force: true
79
+ train_model: false
80
+ inference: false
81
+ results_dir: results
82
+ torch_settings:
83
+ device: null
84
+ debug: false
run_logs/Player-0.log ADDED
The diff for this file is too large to render. See raw diff
 
run_logs/timers.json ADDED
@@ -0,0 +1,368 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.775998592376709,
6
+ "min": 1.6040146350860596,
7
+ "max": 3.2957441806793213,
8
+ "count": 5000
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 35747.30078125,
12
+ "min": 5111.42138671875,
13
+ "max": 138394.046875,
14
+ "count": 5000
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 82.56666666666666,
18
+ "min": 55.28888888888889,
19
+ "max": 999.0,
20
+ "count": 5000
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19816.0,
24
+ "min": 15564.0,
25
+ "max": 24952.0,
26
+ "count": 5000
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1573.510181424287,
30
+ "min": 1176.3367770620202,
31
+ "max": 1643.2444482422695,
32
+ "count": 2891
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 188821.22177091445,
36
+ "min": 2354.063791122488,
37
+ "max": 291336.48131911457,
38
+ "count": 2891
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 49999865.0,
42
+ "min": 9498.0,
43
+ "max": 49999865.0,
44
+ "count": 5000
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 49999865.0,
48
+ "min": 9498.0,
49
+ "max": 49999865.0,
50
+ "count": 5000
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.06021175906062126,
54
+ "min": -0.29010486602783203,
55
+ "max": 0.12045252323150635,
56
+ "count": 5000
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -7.2254109382629395,
60
+ "min": -18.919986724853516,
61
+ "max": 9.369237899780273,
62
+ "count": 5000
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.05843336135149002,
66
+ "min": -0.29126614332199097,
67
+ "max": 0.12659993767738342,
68
+ "count": 5000
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -7.012003421783447,
72
+ "min": -19.16312026977539,
73
+ "max": 9.595020294189453,
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": -0.06249999751647314,
90
+ "min": -0.8743764705517713,
91
+ "max": 0.6009942889213562,
92
+ "count": 5000
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -7.499999701976776,
96
+ "min": -55.73639988899231,
97
+ "max": 43.6576002240181,
98
+ "count": 5000
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.06249999751647314,
102
+ "min": -0.8743764705517713,
103
+ "max": 0.6009942889213562,
104
+ "count": 5000
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -7.499999701976776,
108
+ "min": -55.73639988899231,
109
+ "max": 43.6576002240181,
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": 0.016774558438919486,
126
+ "min": 0.010072278234777817,
127
+ "max": 0.025630577544992168,
128
+ "count": 2341
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.016774558438919486,
132
+ "min": 0.010072278234777817,
133
+ "max": 0.025630577544992168,
134
+ "count": 2341
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.09155314341187477,
138
+ "min": 3.240071249493992e-11,
139
+ "max": 0.09859520792961121,
140
+ "count": 2341
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.09155314341187477,
144
+ "min": 3.240071249493992e-11,
145
+ "max": 0.09859520792961121,
146
+ "count": 2341
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.09291486019889514,
150
+ "min": 4.150054478309813e-11,
151
+ "max": 0.10025302891929945,
152
+ "count": 2341
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.09291486019889514,
156
+ "min": 4.150054478309813e-11,
157
+ "max": 0.10025302891929945,
158
+ "count": 2341
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2341
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2341
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 2341
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 2341
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 2341
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 2341
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1703464603",
200
+ "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
201
+ "command_line_arguments": "\\\\?\\C:\\Users\\chang\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
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": "2.1.2+cpu",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1703627288"
208
+ },
209
+ "total": 162713.8910461,
210
+ "count": 1,
211
+ "self": 2.877047700021649,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.10487579999971786,
215
+ "count": 1,
216
+ "self": 0.10487579999971786
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 162710.9091226,
220
+ "count": 1,
221
+ "self": 95.03098711458733,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 22.870975599962094,
225
+ "count": 250,
226
+ "self": 22.870975599962094
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 162592.78000478543,
230
+ "count": 3285140,
231
+ "self": 99.11501299220254,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 66458.05725349297,
235
+ "count": 3285140,
236
+ "self": 49901.25500668623,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 16496.2410986158,
240
+ "count": 3285140,
241
+ "self": 579.729718210041,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 15916.511380405758,
245
+ "count": 6413848,
246
+ "self": 15916.511380405758
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 60.56114819093136,
252
+ "count": 3285140,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 162593.12074150195,
257
+ "count": 3285140,
258
+ "is_parallel": true,
259
+ "self": 124623.27507769279,
260
+ "children": {
261
+ "steps_from_proto": {
262
+ "total": 0.5632270000055541,
263
+ "count": 500,
264
+ "is_parallel": true,
265
+ "self": 0.10653560005812324,
266
+ "children": {
267
+ "_process_rank_one_or_two_observation": {
268
+ "total": 0.4566913999474309,
269
+ "count": 2000,
270
+ "is_parallel": true,
271
+ "self": 0.4566913999474309
272
+ }
273
+ }
274
+ },
275
+ "UnityEnvironment.step": {
276
+ "total": 37969.28243680915,
277
+ "count": 3285140,
278
+ "is_parallel": true,
279
+ "self": 2018.8212593716598,
280
+ "children": {
281
+ "UnityEnvironment._generate_step_input": {
282
+ "total": 2098.5394663058187,
283
+ "count": 3285140,
284
+ "is_parallel": true,
285
+ "self": 2098.5394663058187
286
+ },
287
+ "communicator.exchange": {
288
+ "total": 26754.034175819048,
289
+ "count": 3285140,
290
+ "is_parallel": true,
291
+ "self": 26754.034175819048
292
+ },
293
+ "steps_from_proto": {
294
+ "total": 7097.887535312628,
295
+ "count": 6570280,
296
+ "is_parallel": true,
297
+ "self": 1349.507690489363,
298
+ "children": {
299
+ "_process_rank_one_or_two_observation": {
300
+ "total": 5748.379844823265,
301
+ "count": 26281120,
302
+ "is_parallel": true,
303
+ "self": 5748.379844823265
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ },
315
+ "trainer_advance": {
316
+ "total": 96035.60773830024,
317
+ "count": 3285140,
318
+ "self": 705.0338465059904,
319
+ "children": {
320
+ "process_trajectory": {
321
+ "total": 13425.446054794105,
322
+ "count": 3285140,
323
+ "self": 13407.045061593923,
324
+ "children": {
325
+ "RLTrainer._checkpoint": {
326
+ "total": 18.40099320018271,
327
+ "count": 100,
328
+ "self": 18.40099320018271
329
+ }
330
+ }
331
+ },
332
+ "_update_policy": {
333
+ "total": 81905.12783700015,
334
+ "count": 2341,
335
+ "self": 8293.239140300793,
336
+ "children": {
337
+ "TorchPOCAOptimizer.update": {
338
+ "total": 73611.88869669936,
339
+ "count": 70230,
340
+ "self": 73611.88869669936
341
+ }
342
+ }
343
+ }
344
+ }
345
+ }
346
+ }
347
+ },
348
+ "trainer_threads": {
349
+ "total": 9.00006853044033e-07,
350
+ "count": 1,
351
+ "self": 9.00006853044033e-07
352
+ },
353
+ "TrainerController._save_models": {
354
+ "total": 0.227154199994402,
355
+ "count": 1,
356
+ "self": 0.05800160000217147,
357
+ "children": {
358
+ "RLTrainer._checkpoint": {
359
+ "total": 0.16915259999223053,
360
+ "count": 1,
361
+ "self": 0.16915259999223053
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": 48499860,
6
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499860.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1703621868.135585,
9
+ "auxillary_file_paths": [
10
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499860.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 48999946,
15
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999946.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1703623713.5747406,
18
+ "auxillary_file_paths": [
19
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999946.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 49499990,
24
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499990.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1703625514.037782,
27
+ "auxillary_file_paths": [
28
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499990.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 49999865,
33
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999865.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1703627285.4809556,
36
+ "auxillary_file_paths": [
37
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999865.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 50000036,
42
+ "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000036.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1703627285.704455,
45
+ "auxillary_file_paths": [
46
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000036.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1571.5942980926663,
51
+ "final_checkpoint": {
52
+ "steps": 50000036,
53
+ "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1703627285.704455,
56
+ "auxillary_file_paths": [
57
+ "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000036.pt"
58
+ ]
59
+ }
60
+ },
61
+ "metadata": {
62
+ "stats_format_version": "0.3.0",
63
+ "mlagents_version": "1.1.0.dev0",
64
+ "torch_version": "2.1.2+cpu"
65
+ }
66
+ }