Hugging Face's logo

SmellyKat
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
SmellyKat commited on
Commit
1b92f80
·
1 Parent(s): 9e9f76c

First Push

Browse files
Files changed (20) hide show
  1. .DS_Store +0 -0
  2. README.md +35 -0
  3. SoccerTwos.onnx +3 -0
  4. SoccerTwos/SoccerTwos-24999622.onnx +3 -0
  5. SoccerTwos/SoccerTwos-24999622.pt +3 -0
  6. SoccerTwos/SoccerTwos-25499822.onnx +3 -0
  7. SoccerTwos/SoccerTwos-25499822.pt +3 -0
  8. SoccerTwos/SoccerTwos-25999122.onnx +3 -0
  9. SoccerTwos/SoccerTwos-25999122.pt +3 -0
  10. SoccerTwos/SoccerTwos-26499322.onnx +3 -0
  11. SoccerTwos/SoccerTwos-26499322.pt +3 -0
  12. SoccerTwos/SoccerTwos-26509322.onnx +3 -0
  13. SoccerTwos/SoccerTwos-26509322.pt +3 -0
  14. SoccerTwos/checkpoint.pt +3 -0
  15. SoccerTwos/events.out.tfevents.1693989561.eduroam-193-157-214-204.wlan.uio.no.75697.0 +3 -0
  16. config.json +1 -0
  17. configuration.yaml +82 -0
  18. run_logs/Player-0.log +0 -0
  19. run_logs/timers.json +368 -0
  20. run_logs/training_status.json +66 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
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: SmellyKat/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:a06a1096776e8b963b4a8f87911cd66b71a345359bc7d91b78d2976b8bb0c5a8
3
+ size 1764633
SoccerTwos/SoccerTwos-24999622.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a4ea1b9245d5e7a2f3d043175fb78bfb7aa1091cdac96f97cbe3efefe70802
3
+ size 1764633
SoccerTwos/SoccerTwos-24999622.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17385f5ff554bbaa6c44eb60fc8c7ca66a259f679960687a514b4b4cdbc1f699
3
+ size 28421201
SoccerTwos/SoccerTwos-25499822.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a70bca249f7261bc9c8f2772014af52aff83db40e51a9acea2af304cf8cbce1
3
+ size 1764633
SoccerTwos/SoccerTwos-25499822.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569eb70094068203b0fb862b5f88524a19dcde0549f8f0dcb531e5ae67b3a36d
3
+ size 28421201
SoccerTwos/SoccerTwos-25999122.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839e6004e5a9d762a26e73afe8417e83d4f5daf7cba929f26be4b4664e1aafe8
3
+ size 1764633
SoccerTwos/SoccerTwos-25999122.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3d869dab9185d29866d7d77341e9b649416c024c310985c9e201526137cc40
3
+ size 28421201
SoccerTwos/SoccerTwos-26499322.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06a1096776e8b963b4a8f87911cd66b71a345359bc7d91b78d2976b8bb0c5a8
3
+ size 1764633
SoccerTwos/SoccerTwos-26499322.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e840bc8ffaca2ccd660ce05b1556a4f260b3cee44e342c7e016fc3b7778801c3
3
+ size 28421201
SoccerTwos/SoccerTwos-26509322.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06a1096776e8b963b4a8f87911cd66b71a345359bc7d91b78d2976b8bb0c5a8
3
+ size 1764633
SoccerTwos/SoccerTwos-26509322.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c41b2b680d01595a20f28b7e8f9ab9c6ede94a8eae15474ec5c952fe676bf22
3
+ size 28421201
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c41b2b680d01595a20f28b7e8f9ab9c6ede94a8eae15474ec5c952fe676bf22
3
+ size 28421201
SoccerTwos/events.out.tfevents.1693989561.eduroam-193-157-214-204.wlan.uio.no.75697.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d30bf3e9bbf66d26c6a94787f0dc673d5ba29042530728d8636df9897fd80c3
3
+ size 3554241
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, "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": "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 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: 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
+ 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: SoccerTwos2
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/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": 1.5010002851486206,
6
+ "min": 0.14359895884990692,
7
+ "max": 3.2957725524902344,
8
+ "count": 2650
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 25072.708984375,
12
+ "min": 2472.19970703125,
13
+ "max": 157598.3125,
14
+ "count": 2650
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 999.0,
18
+ "min": 449.0,
19
+ "max": 999.0,
20
+ "count": 2650
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19980.0,
24
+ "min": 6812.0,
25
+ "max": 31968.0,
26
+ "count": 2650
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1192.6688295986764,
30
+ "min": 1182.9818516654466,
31
+ "max": 1201.1452901447674,
32
+ "count": 213
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 2385.337659197353,
36
+ "min": 2365.963703330893,
37
+ "max": 14332.572764257897,
38
+ "count": 213
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 26499322.0,
42
+ "min": 9202.0,
43
+ "max": 26499322.0,
44
+ "count": 2650
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 26499322.0,
48
+ "min": 9202.0,
49
+ "max": 26499322.0,
50
+ "count": 2650
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.0040586600080132484,
54
+ "min": -0.031186968088150024,
55
+ "max": 0.01596347615122795,
56
+ "count": 2650
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 0.040586601942777634,
60
+ "min": -0.4029216468334198,
61
+ "max": 0.19755713641643524,
62
+ "count": 2650
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.004023420624434948,
66
+ "min": -0.02649976685643196,
67
+ "max": 0.015397198498249054,
68
+ "count": 2650
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 0.04023420438170433,
72
+ "min": -0.3764663338661194,
73
+ "max": 0.1897004246711731,
74
+ "count": 2650
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 2650
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 2650
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.0,
90
+ "min": -0.5833333333333334,
91
+ "max": 0.2356333335240682,
92
+ "count": 2650
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 0.0,
96
+ "min": -7.0,
97
+ "max": 2.8276000022888184,
98
+ "count": 2650
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.0,
102
+ "min": -0.5833333333333334,
103
+ "max": 0.2356333335240682,
104
+ "count": 2650
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 0.0,
108
+ "min": -7.0,
109
+ "max": 2.8276000022888184,
110
+ "count": 2650
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 2650
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 2650
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.019118176718863348,
126
+ "min": 0.009272572166325214,
127
+ "max": 0.02454209647451838,
128
+ "count": 1211
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.019118176718863348,
132
+ "min": 0.009272572166325214,
133
+ "max": 0.02454209647451838,
134
+ "count": 1211
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 1.11551125640356e-07,
138
+ "min": 4.668687362344622e-12,
139
+ "max": 0.007558033487293869,
140
+ "count": 1211
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 1.11551125640356e-07,
144
+ "min": 4.668687362344622e-12,
145
+ "max": 0.007558033487293869,
146
+ "count": 1211
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 1.1197233265036744e-07,
150
+ "min": 8.057526087318356e-12,
151
+ "max": 0.007522881041707782,
152
+ "count": 1211
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 1.1197233265036744e-07,
156
+ "min": 8.057526087318356e-12,
157
+ "max": 0.007522881041707782,
158
+ "count": 1211
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 1211
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 1211
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000004,
175
+ "max": 0.20000000000000007,
176
+ "count": 1211
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000004,
181
+ "max": 0.20000000000000007,
182
+ "count": 1211
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 1211
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 1211
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1693989555",
200
+ "python_version": "3.9.17 (main, Jul 5 2023, 16:17:03) \n[Clang 14.0.6 ]",
201
+ "command_line_arguments": "/Users/lisbethsommervoll/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos2 --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": "1.11.0",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1694162905"
208
+ },
209
+ "total": 148423.464857715,
210
+ "count": 1,
211
+ "self": 1.2090299140254501,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.04708759400000018,
215
+ "count": 1,
216
+ "self": 0.04708759400000018
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 148422.208740207,
220
+ "count": 1,
221
+ "self": 58.314802076871274,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 20.85854673906688,
225
+ "count": 132,
226
+ "self": 20.85854673906688
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 148342.66568526806,
230
+ "count": 1726143,
231
+ "self": 60.4048593302432,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 47026.48867663683,
235
+ "count": 1726143,
236
+ "self": 38877.853761161576,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 8111.854864469853,
240
+ "count": 1726143,
241
+ "self": 377.2230402806035,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 7734.6318241892495,
245
+ "count": 3428912,
246
+ "self": 7734.6318241892495
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 36.78005100539961,
252
+ "count": 1726143,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 148315.02208223878,
257
+ "count": 1726143,
258
+ "is_parallel": true,
259
+ "self": 116629.18104768549,
260
+ "children": {
261
+ "steps_from_proto": {
262
+ "total": 0.4370631660573432,
263
+ "count": 264,
264
+ "is_parallel": true,
265
+ "self": 0.08902383719041396,
266
+ "children": {
267
+ "_process_rank_one_or_two_observation": {
268
+ "total": 0.34803932886692923,
269
+ "count": 1056,
270
+ "is_parallel": true,
271
+ "self": 0.34803932886692923
272
+ }
273
+ }
274
+ },
275
+ "UnityEnvironment.step": {
276
+ "total": 31685.40397138723,
277
+ "count": 1726143,
278
+ "is_parallel": true,
279
+ "self": 1835.9857131515419,
280
+ "children": {
281
+ "UnityEnvironment._generate_step_input": {
282
+ "total": 1079.5908657014559,
283
+ "count": 1726143,
284
+ "is_parallel": true,
285
+ "self": 1079.5908657014559
286
+ },
287
+ "communicator.exchange": {
288
+ "total": 23518.560639100124,
289
+ "count": 1726143,
290
+ "is_parallel": true,
291
+ "self": 23518.560639100124
292
+ },
293
+ "steps_from_proto": {
294
+ "total": 5251.266753434107,
295
+ "count": 3452286,
296
+ "is_parallel": true,
297
+ "self": 1079.0703113064428,
298
+ "children": {
299
+ "_process_rank_one_or_two_observation": {
300
+ "total": 4172.196442127664,
301
+ "count": 13809144,
302
+ "is_parallel": true,
303
+ "self": 4172.196442127664
304
+ }
305
+ }
306
+ }
307
+ }
308
+ }
309
+ }
310
+ }
311
+ }
312
+ }
313
+ }
314
+ },
315
+ "trainer_advance": {
316
+ "total": 101255.77214930099,
317
+ "count": 1726143,
318
+ "self": 386.1206120074203,
319
+ "children": {
320
+ "process_trajectory": {
321
+ "total": 11635.649203153596,
322
+ "count": 1726143,
323
+ "self": 11618.937049082608,
324
+ "children": {
325
+ "RLTrainer._checkpoint": {
326
+ "total": 16.712154070988163,
327
+ "count": 53,
328
+ "self": 16.712154070988163
329
+ }
330
+ }
331
+ },
332
+ "_update_policy": {
333
+ "total": 89234.00233413996,
334
+ "count": 1211,
335
+ "self": 7025.09280576685,
336
+ "children": {
337
+ "TorchPOCAOptimizer.update": {
338
+ "total": 82208.90952837311,
339
+ "count": 36339,
340
+ "self": 82208.90952837311
341
+ }
342
+ }
343
+ }
344
+ }
345
+ }
346
+ }
347
+ },
348
+ "trainer_threads": {
349
+ "total": 2.1329906303435564e-06,
350
+ "count": 1,
351
+ "self": 2.1329906303435564e-06
352
+ },
353
+ "TrainerController._save_models": {
354
+ "total": 0.36970398999983445,
355
+ "count": 1,
356
+ "self": 0.0034137969778385013,
357
+ "children": {
358
+ "RLTrainer._checkpoint": {
359
+ "total": 0.36629019302199595,
360
+ "count": 1,
361
+ "self": 0.36629019302199595
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": 24999622,
6
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-24999622.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1694152540.8428092,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-24999622.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 25499822,
15
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-25499822.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1694155337.468823,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-25499822.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 25999122,
24
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-25999122.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1694158268.8324249,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-25999122.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 26499322,
33
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-26499322.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1694162885.3094,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-26499322.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 26509322,
42
+ "file_path": "results/SoccerTwos2/SoccerTwos/SoccerTwos-26509322.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1694162904.171437,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-26509322.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1192.9181100428218,
51
+ "final_checkpoint": {
52
+ "steps": 26509322,
53
+ "file_path": "results/SoccerTwos2/SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1694162904.171437,
56
+ "auxillary_file_paths": [
57
+ "results/SoccerTwos2/SoccerTwos/SoccerTwos-26509322.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
+ }