Hugging Face's logo

WIS
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
WIS commited on
Commit
1d39dc8
•
1 Parent(s): 7ada632

First Push

Browse files
Files changed (19) hide show
  1. README.md +35 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-48499886.onnx +3 -0
  4. SoccerTwos/SoccerTwos-48499886.pt +3 -0
  5. SoccerTwos/SoccerTwos-48999993.onnx +3 -0
  6. SoccerTwos/SoccerTwos-48999993.pt +3 -0
  7. SoccerTwos/SoccerTwos-49499977.onnx +3 -0
  8. SoccerTwos/SoccerTwos-49499977.pt +3 -0
  9. SoccerTwos/SoccerTwos-49999902.onnx +3 -0
  10. SoccerTwos/SoccerTwos-49999902.pt +3 -0
  11. SoccerTwos/SoccerTwos-50000316.onnx +3 -0
  12. SoccerTwos/SoccerTwos-50000316.pt +3 -0
  13. SoccerTwos/checkpoint.pt +3 -0
  14. SoccerTwos/events.out.tfevents.1705906522.mlxlabjuqzifhx65ab4ad1-20240120042346-wcic0a-master.11322.0 +3 -0
  15. config.json +1 -0
  16. configuration.yaml +84 -0
  17. run_logs/Player-0.log +0 -0
  18. run_logs/timers.json +424 -0
  19. run_logs/training_status.json +66 -0
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: WIS/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:cd0cfb65800b380244f34589a1053f42fc7a90bfa7a8062cc16a27e652886504
3
+ size 1768747
SoccerTwos/SoccerTwos-48499886.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c9ff4e8f66acc14d2a83bd07584f6ec0149c825792074411ebca4f82c55fd21
3
+ size 1768747
SoccerTwos/SoccerTwos-48499886.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7575dd9dd05da76e7ca8a2c883b2419832288532c8dc471efc4c6bee9bd917
3
+ size 28430482
SoccerTwos/SoccerTwos-48999993.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c0fb6bf5442f4f451bb4410d70c57de0a3e06ebb758b53c7f6b344c0fe1a35
3
+ size 1768747
SoccerTwos/SoccerTwos-48999993.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e23a55ae3944982005f07263fb427b4f797eee6104d6252682bdc7b45891d5d
3
+ size 28430482
SoccerTwos/SoccerTwos-49499977.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0078aadae735c6d64a08625f149d0a686f8bf733d384833c292775a9bc652e
3
+ size 1768747
SoccerTwos/SoccerTwos-49499977.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3b276833e04048d6ea59ea5d6c62ff063e2153ab185f8c5421fe44597d4237
3
+ size 28430482
SoccerTwos/SoccerTwos-49999902.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0cfb65800b380244f34589a1053f42fc7a90bfa7a8062cc16a27e652886504
3
+ size 1768747
SoccerTwos/SoccerTwos-49999902.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57abd9e000de508873b511c2fa6ac2e9213ddf76a6f4e8a09b886b5bf277525
3
+ size 28430482
SoccerTwos/SoccerTwos-50000316.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0cfb65800b380244f34589a1053f42fc7a90bfa7a8062cc16a27e652886504
3
+ size 1768747
SoccerTwos/SoccerTwos-50000316.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd314299920c9310c2a9be0e6c0c30ac17bec7ef60d6b1c768e34dd32d8a635
3
+ size 28430482
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca5fa733af439e3347d6343504573ba00ba064f21a47d7051c2c8291eeee604
3
+ size 28429366
SoccerTwos/events.out.tfevents.1705906522.mlxlabjuqzifhx65ab4ad1-20240120042346-wcic0a-master.11322.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d7bf4a54b2a84c513022fe5fb85ee567ae6ca4652b4a0c7387aa0aedc4d539
3
+ size 34062307
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.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}
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.x86_64
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: false
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 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.409071922302246,
6
+ "min": 0.580023467540741,
7
+ "max": 3.2957353591918945,
8
+ "count": 5000
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 28406.890625,
12
+ "min": 5988.8271484375,
13
+ "max": 145126.765625,
14
+ "count": 5000
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 69.3972602739726,
18
+ "min": 44.054545454545455,
19
+ "max": 999.0,
20
+ "count": 5000
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 20264.0,
24
+ "min": 12164.0,
25
+ "max": 27920.0,
26
+ "count": 5000
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1542.8781649418193,
30
+ "min": 1184.7955637147627,
31
+ "max": 1625.1740943820848,
32
+ "count": 3265
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 225260.21208150563,
36
+ "min": 2374.3217125616216,
37
+ "max": 351378.12929364503,
38
+ "count": 3265
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 49999902.0,
42
+ "min": 9976.0,
43
+ "max": 49999902.0,
44
+ "count": 5000
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 49999902.0,
48
+ "min": 9976.0,
49
+ "max": 49999902.0,
50
+ "count": 5000
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.04849886894226074,
54
+ "min": -0.14891868829727173,
55
+ "max": 0.197387233376503,
56
+ "count": 5000
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -7.032336235046387,
60
+ "min": -25.018339157104492,
61
+ "max": 21.909982681274414,
62
+ "count": 5000
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.04817768931388855,
66
+ "min": -0.14785706996917725,
67
+ "max": 0.19496957957744598,
68
+ "count": 5000
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -6.985764980316162,
72
+ "min": -24.83998680114746,
73
+ "max": 21.64162254333496,
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": -0.14953103558770542,
90
+ "min": -0.5992666681607565,
91
+ "max": 0.4935333345617567,
92
+ "count": 5000
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": -21.682000160217285,
96
+ "min": -59.1327999830246,
97
+ "max": 46.43540012836456,
98
+ "count": 5000
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": -0.14953103558770542,
102
+ "min": -0.5992666681607565,
103
+ "max": 0.4935333345617567,
104
+ "count": 5000
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": -21.682000160217285,
108
+ "min": -59.1327999830246,
109
+ "max": 46.43540012836456,
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": 0.018001814029412345,
126
+ "min": 0.009255766456529575,
127
+ "max": 0.026368796251093347,
128
+ "count": 2370
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.018001814029412345,
132
+ "min": 0.009255766456529575,
133
+ "max": 0.026368796251093347,
134
+ "count": 2370
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.08666058033704757,
138
+ "min": 3.279833690518948e-11,
139
+ "max": 0.11784214849273364,
140
+ "count": 2370
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.08666058033704757,
144
+ "min": 3.279833690518948e-11,
145
+ "max": 0.11784214849273364,
146
+ "count": 2370
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.08756576379140218,
150
+ "min": 3.7002813429073043e-11,
151
+ "max": 0.11892481545607249,
152
+ "count": 2370
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.08756576379140218,
156
+ "min": 3.7002813429073043e-11,
157
+ "max": 0.11892481545607249,
158
+ "count": 2370
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2370
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2370
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000004,
175
+ "max": 0.20000000000000007,
176
+ "count": 2370
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000004,
181
+ "max": 0.20000000000000007,
182
+ "count": 2370
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 2370
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 2370
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1705906520",
200
+ "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
201
+ "command_line_arguments": "/root/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --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": "2.1.2+cu121",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1706014077"
208
+ },
209
+ "total": 107556.39236933202,
210
+ "count": 1,
211
+ "self": 0.4893856640555896,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.09685415698913857,
215
+ "count": 1,
216
+ "self": 0.09685415698913857
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 107555.80612951098,
220
+ "count": 1,
221
+ "self": 56.057607389520854,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 12.113171444681939,
225
+ "count": 250,
226
+ "self": 12.113171444681939
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 107487.14703818178,
230
+ "count": 3358224,
231
+ "self": 53.167223570810165,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 47161.045734404994,
235
+ "count": 3358224,
236
+ "self": 37205.82435472682,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 9922.062924618716,
240
+ "count": 3358224,
241
+ "self": 372.13904499076307,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 9549.923879627953,
245
+ "count": 6350498,
246
+ "self": 9549.923879627953
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 33.15845505945617,
252
+ "count": 3358224,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 107466.25550758577,
257
+ "count": 3358224,
258
+ "is_parallel": true,
259
+ "self": 77240.05800597148,
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": 0.0024395579821430147,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0007359739975072443,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.0017035839846357703,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.0017035839846357703
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.02229533198988065,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0005469299503602087,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0004575889906845987,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0004575889906845987
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.019752520020119846,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.019752520020119846
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.001538293028715998,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.0003324220306240022,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0012058709980919957,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0012058709980919957
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 30225.796755509567,
319
+ "count": 3358223,
320
+ "is_parallel": true,
321
+ "self": 1597.375346368237,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 1068.764909645426,
325
+ "count": 3358223,
326
+ "is_parallel": true,
327
+ "self": 1068.764909645426
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 22985.073879790318,
331
+ "count": 3358223,
332
+ "is_parallel": true,
333
+ "self": 22985.073879790318
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 4574.582619705587,
337
+ "count": 6716446,
338
+ "is_parallel": true,
339
+ "self": 858.5062123311218,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 3716.076407374465,
343
+ "count": 26865784,
344
+ "is_parallel": true,
345
+ "self": 3716.076407374465
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.40074610471492633,
353
+ "count": 498,
354
+ "is_parallel": true,
355
+ "self": 0.07684651366434991,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.3238995910505764,
359
+ "count": 1992,
360
+ "is_parallel": true,
361
+ "self": 0.3238995910505764
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 60272.934080205974,
373
+ "count": 3358224,
374
+ "self": 490.5562912662863,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 9244.681141626206,
378
+ "count": 3358224,
379
+ "self": 9102.18898997939,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 142.49215164681664,
383
+ "count": 100,
384
+ "self": 142.49215164681664
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 50537.69664731348,
390
+ "count": 2370,
391
+ "self": 5545.043199257401,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 44992.65344805608,
395
+ "count": 71109,
396
+ "self": 44992.65344805608
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 8.729984983801842e-07,
406
+ "count": 1,
407
+ "self": 8.729984983801842e-07
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.48831162200076506,
411
+ "count": 1,
412
+ "self": 0.010910457989666611,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.47740116401109844,
416
+ "count": 1,
417
+ "self": 0.47740116401109844
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": 48499886,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499886.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1706009690.4836137,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48499886.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 48999993,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999993.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1706011211.3690562,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48999993.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 49499977,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499977.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1706012613.2856994,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49499977.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 49999902,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999902.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1706014076.1768775,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49999902.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 50000316,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000316.onnx",
43
+ "reward": 0.0,
44
+ "creation_time": 1706014076.7248127,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000316.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1542.1803939018384,
51
+ "final_checkpoint": {
52
+ "steps": 50000316,
53
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
+ "reward": 0.0,
55
+ "creation_time": 1706014076.7248127,
56
+ "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000316.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+cu121"
65
+ }
66
+ }