Hugging Face's logo

SpriteLi
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SoccerTwos
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files
xet
 Metrics Community
SpriteLi commited on
Commit
2a56c09
·
verified ·
1 Parent(s): 97ba55a

First Push

Browse files
Files changed (20) hide show
  1. README.md +35 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-48499986.onnx +3 -0
  4. SoccerTwos/SoccerTwos-48499986.pt +3 -0
  5. SoccerTwos/SoccerTwos-48999989.onnx +3 -0
  6. SoccerTwos/SoccerTwos-48999989.pt +3 -0
  7. SoccerTwos/SoccerTwos-49499970.onnx +3 -0
  8. SoccerTwos/SoccerTwos-49499970.pt +3 -0
  9. SoccerTwos/SoccerTwos-49999898.onnx +3 -0
  10. SoccerTwos/SoccerTwos-49999898.pt +3 -0
  11. SoccerTwos/SoccerTwos-50000004.onnx +3 -0
  12. SoccerTwos/SoccerTwos-50000004.pt +3 -0
  13. SoccerTwos/checkpoint.pt +3 -0
  14. SoccerTwos/events.out.tfevents.1746693650.jididu-OMEN-by-HP-25L-Gaming-Desktop-GT14-2xxx.113783.0 +3 -0
  15. SoccerTwos/events.out.tfevents.1746693671.jididu-OMEN-by-HP-25L-Gaming-Desktop-GT14-2xxx.113989.0 +3 -0
  16. config.json +1 -0
  17. configuration.yaml +84 -0
  18. run_logs/Player-0.log +0 -0
  19. run_logs/timers.json +424 -0
  20. 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: SpriteLi/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:bc144d3a36bddc64dcf07a41c3907dbac8e99b017dd59b0d29c42630b2474359
3
+ size 1768747
SoccerTwos/SoccerTwos-48499986.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca995fd87696efb095415abc29bfe1934fd12784c4af4cb1c5a833285335425
3
+ size 1768747
SoccerTwos/SoccerTwos-48499986.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcfe99c79fccb323e16e5bbc85826128c1770da38472d5eef73a9b722998dba
3
+ size 28432631
SoccerTwos/SoccerTwos-48999989.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87344f118bc43e68e70b2b1e408ea0a2b8e640365268d4ac68575df3146a749
3
+ size 1768747
SoccerTwos/SoccerTwos-48999989.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfab95695543876079bf068fe993dd815645c615ebda6ca4748f362077cdcc8
3
+ size 28432631
SoccerTwos/SoccerTwos-49499970.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828c2ad801681916137b1e88986b5a55765deedfa92e2147f7b1d4bfdd0d5238
3
+ size 1768747
SoccerTwos/SoccerTwos-49499970.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7ee53cc8763134b5490dd99a0adeec4f8793492a3998fbc06cf3139baa1d7d
3
+ size 28432631
SoccerTwos/SoccerTwos-49999898.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc144d3a36bddc64dcf07a41c3907dbac8e99b017dd59b0d29c42630b2474359
3
+ size 1768747
SoccerTwos/SoccerTwos-49999898.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d8acdd73cdaa4c21b732268714780dafe9635416c86285c85e474bed44bda1
3
+ size 28432631
SoccerTwos/SoccerTwos-50000004.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc144d3a36bddc64dcf07a41c3907dbac8e99b017dd59b0d29c42630b2474359
3
+ size 1768747
SoccerTwos/SoccerTwos-50000004.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1deb72a2d43ba12afafe7718f0b9aadf7ad6930f2e18d4c667c54cb57f2768f6
3
+ size 28432631
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879926bdab0ae27e0931060f4f95a28da2dfc5bcc499ec6600a32a113b7fd7e2
3
+ size 28431497
SoccerTwos/events.out.tfevents.1746693650.jididu-OMEN-by-HP-25L-Gaming-Desktop-GT14-2xxx.113783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010982ca7c5df10301c9edd9354e8b354200c209591f768a8e97069fc3efe3c5
3
+ size 1241
SoccerTwos/events.out.tfevents.1746693671.jididu-OMEN-by-HP-25L-Gaming-Desktop-GT14-2xxx.113989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c9f8ff793aeb9980da73c574df1d7e08f8b552fc9b5e2ac66c868f314598bb
3
+ size 37613755
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": true, "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: true
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": 1.4352360963821411,
6
+ "min": 1.0373258590698242,
7
+ "max": 3.295711040496826,
8
+ "count": 5000
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 27786.169921875,
12
+ "min": 3776.663330078125,
13
+ "max": 130095.5390625,
14
+ "count": 5000
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 75.93846153846154,
18
+ "min": 35.0,
19
+ "max": 999.0,
20
+ "count": 5000
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19744.0,
24
+ "min": 140.0,
25
+ "max": 31968.0,
26
+ "count": 5000
27
+ },
28
+ "SoccerTwos.Step.mean": {
29
+ "value": 49999898.0,
30
+ "min": 9000.0,
31
+ "max": 49999898.0,
32
+ "count": 5000
33
+ },
34
+ "SoccerTwos.Step.sum": {
35
+ "value": 49999898.0,
36
+ "min": 9000.0,
37
+ "max": 49999898.0,
38
+ "count": 5000
39
+ },
40
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
41
+ "value": 0.01427179854363203,
42
+ "min": -0.16231806576251984,
43
+ "max": 0.12857086956501007,
44
+ "count": 5000
45
+ },
46
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
47
+ "value": 1.8553338050842285,
48
+ "min": -21.588302612304688,
49
+ "max": 19.028488159179688,
50
+ "count": 5000
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
53
+ "value": 0.01561132911592722,
54
+ "min": -0.16288472712039948,
55
+ "max": 0.12368025630712509,
56
+ "count": 5000
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
59
+ "value": 2.029472827911377,
60
+ "min": -21.66366958618164,
61
+ "max": 18.304677963256836,
62
+ "count": 5000
63
+ },
64
+ "SoccerTwos.Environment.CumulativeReward.mean": {
65
+ "value": 0.0,
66
+ "min": 0.0,
67
+ "max": 0.0,
68
+ "count": 5000
69
+ },
70
+ "SoccerTwos.Environment.CumulativeReward.sum": {
71
+ "value": 0.0,
72
+ "min": 0.0,
73
+ "max": 0.0,
74
+ "count": 5000
75
+ },
76
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
77
+ "value": 0.02923230712230389,
78
+ "min": -0.7604521720305734,
79
+ "max": 0.5379627832146578,
80
+ "count": 5000
81
+ },
82
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
83
+ "value": 3.8001999258995056,
84
+ "min": -57.784800350666046,
85
+ "max": 47.87719976902008,
86
+ "count": 5000
87
+ },
88
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
89
+ "value": 0.02923230712230389,
90
+ "min": -0.7604521720305734,
91
+ "max": 0.5379627832146578,
92
+ "count": 5000
93
+ },
94
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
95
+ "value": 3.8001999258995056,
96
+ "min": -57.784800350666046,
97
+ "max": 47.87719976902008,
98
+ "count": 5000
99
+ },
100
+ "SoccerTwos.IsTraining.mean": {
101
+ "value": 1.0,
102
+ "min": 1.0,
103
+ "max": 1.0,
104
+ "count": 5000
105
+ },
106
+ "SoccerTwos.IsTraining.sum": {
107
+ "value": 1.0,
108
+ "min": 1.0,
109
+ "max": 1.0,
110
+ "count": 5000
111
+ },
112
+ "SoccerTwos.Self-play.ELO.mean": {
113
+ "value": 1799.8119557276668,
114
+ "min": 1169.0176856792277,
115
+ "max": 1849.995444885142,
116
+ "count": 3668
117
+ },
118
+ "SoccerTwos.Self-play.ELO.sum": {
119
+ "value": 233975.5542445967,
120
+ "min": 2338.0353713584554,
121
+ "max": 355380.0255735362,
122
+ "count": 3668
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.018310294121814272,
126
+ "min": 0.009828699003749837,
127
+ "max": 0.02874177086632699,
128
+ "count": 2379
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.018310294121814272,
132
+ "min": 0.009828699003749837,
133
+ "max": 0.02874177086632699,
134
+ "count": 2379
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.08930967599153519,
138
+ "min": 3.3262288987960056e-11,
139
+ "max": 0.10120151763161024,
140
+ "count": 2379
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.08930967599153519,
144
+ "min": 3.3262288987960056e-11,
145
+ "max": 0.10120151763161024,
146
+ "count": 2379
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.09039074753721556,
150
+ "min": 3.783137125327555e-11,
151
+ "max": 0.1030238226056099,
152
+ "count": 2379
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.09039074753721556,
156
+ "min": 3.783137125327555e-11,
157
+ "max": 0.1030238226056099,
158
+ "count": 2379
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 2379
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 2379
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.19999999999999996,
175
+ "max": 0.20000000000000007,
176
+ "count": 2379
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.19999999999999996,
181
+ "max": 0.20000000000000007,
182
+ "count": 2379
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005,
187
+ "max": 0.005000000000000001,
188
+ "count": 2379
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005,
193
+ "max": 0.005000000000000001,
194
+ "count": 2379
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1746693670",
200
+ "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
201
+ "command_line_arguments": "/mnt/data_disk/conda_envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
202
+ "mlagents_version": "1.2.0.dev0",
203
+ "mlagents_envs_version": "1.2.0.dev0",
204
+ "communication_protocol_version": "1.5.0",
205
+ "pytorch_version": "2.7.0+cu126",
206
+ "numpy_version": "1.23.5",
207
+ "end_time_seconds": "1746739895"
208
+ },
209
+ "total": 46224.794120538005,
210
+ "count": 1,
211
+ "self": 0.1674580069957301,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.010993156000040472,
215
+ "count": 1,
216
+ "self": 0.010993156000040472
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 46224.61566937501,
220
+ "count": 1,
221
+ "self": 42.65619713823253,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 8.090363160037668,
225
+ "count": 250,
226
+ "self": 8.090363160037668
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 46173.77667533774,
230
+ "count": 3339229,
231
+ "self": 42.236754013138125,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 36606.93445628509,
235
+ "count": 3339229,
236
+ "self": 26806.962803515606,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 9772.420487577998,
240
+ "count": 3339229,
241
+ "self": 292.34762571832107,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 9480.072861859677,
245
+ "count": 6339830,
246
+ "self": 9480.072861859677
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 27.55116519148578,
252
+ "count": 3339229,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 46169.90348756597,
257
+ "count": 3339229,
258
+ "is_parallel": true,
259
+ "self": 24367.764377407002,
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": 0.0017587430193088949,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0004506730329012498,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.001308069986407645,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.001308069986407645
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.016087823009002022,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0003468790091574192,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0002764490054687485,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0002764490054687485
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.01448543400329072,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.01448543400329072
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0009790609910851344,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00019002497720066458,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0007890360138844699,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0007890360138844699
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 21801.886607807086,
319
+ "count": 3339228,
320
+ "is_parallel": true,
321
+ "self": 1183.0336056348024,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 698.5813262571901,
325
+ "count": 3339228,
326
+ "is_parallel": true,
327
+ "self": 698.5813262571901
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 16671.049981842007,
331
+ "count": 3339228,
332
+ "is_parallel": true,
333
+ "self": 16671.049981842007
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 3249.221694073087,
337
+ "count": 6678456,
338
+ "is_parallel": true,
339
+ "self": 596.9331710937549,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 2652.288522979332,
343
+ "count": 26713824,
344
+ "is_parallel": true,
345
+ "self": 2652.288522979332
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.2525023518828675,
353
+ "count": 498,
354
+ "is_parallel": true,
355
+ "self": 0.04685448852251284,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.20564786336035468,
359
+ "count": 1992,
360
+ "is_parallel": true,
361
+ "self": 0.20564786336035468
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 9524.605465039509,
373
+ "count": 3339229,
374
+ "self": 329.08162470001844,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 3966.8530807326606,
378
+ "count": 3339229,
379
+ "self": 3957.325599080723,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 9.527481651937705,
383
+ "count": 100,
384
+ "self": 9.527481651937705
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 5228.67075960683,
390
+ "count": 2379,
391
+ "self": 3379.2039724364877,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 1849.4667871703423,
395
+ "count": 71382,
396
+ "self": 1849.4667871703423
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 6.210029823705554e-07,
406
+ "count": 1,
407
+ "self": 6.210029823705554e-07
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.09243311799946241,
411
+ "count": 1,
412
+ "self": 0.001005106998491101,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.09142801100097131,
416
+ "count": 1,
417
+ "self": 0.09142801100097131
418
+ }
419
+ }
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "stats_format_version": "0.3.0",
4
+ "mlagents_version": "1.2.0.dev0",
5
+ "torch_version": "2.7.0+cu126"
6
+ },
7
+ "SoccerTwos": {
8
+ "elo": 1797.389045447255,
9
+ "checkpoints": [
10
+ {
11
+ "steps": 48499986,
12
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499986.onnx",
13
+ "reward": 0.0,
14
+ "creation_time": 1746738483.2138023,
15
+ "auxillary_file_paths": [
16
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48499986.pt"
17
+ ]
18
+ },
19
+ {
20
+ "steps": 48999989,
21
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999989.onnx",
22
+ "reward": 0.0,
23
+ "creation_time": 1746738955.5656302,
24
+ "auxillary_file_paths": [
25
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-48999989.pt"
26
+ ]
27
+ },
28
+ {
29
+ "steps": 49499970,
30
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499970.onnx",
31
+ "reward": 0.0,
32
+ "creation_time": 1746739428.2138126,
33
+ "auxillary_file_paths": [
34
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49499970.pt"
35
+ ]
36
+ },
37
+ {
38
+ "steps": 49999898,
39
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999898.onnx",
40
+ "reward": 0.0,
41
+ "creation_time": 1746739895.469124,
42
+ "auxillary_file_paths": [
43
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-49999898.pt"
44
+ ]
45
+ },
46
+ {
47
+ "steps": 50000004,
48
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000004.onnx",
49
+ "reward": 0.0,
50
+ "creation_time": 1746739895.5683079,
51
+ "auxillary_file_paths": [
52
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000004.pt"
53
+ ]
54
+ }
55
+ ],
56
+ "final_checkpoint": {
57
+ "steps": 50000004,
58
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
59
+ "reward": 0.0,
60
+ "creation_time": 1746739895.5683079,
61
+ "auxillary_file_paths": [
62
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-50000004.pt"
63
+ ]
64
+ }
65
+ }
66
+ }