Hugging Face's logo

Ktang2k
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
Ktang2k commited on
Commit
093e557
•
1 Parent(s): f532c4c

First Push

Browse files
Files changed (18) hide show
  1. README.md +31 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-4499899.onnx +3 -0
  4. SoccerTwos/SoccerTwos-4499899.pt +3 -0
  5. SoccerTwos/SoccerTwos-4999992.onnx +3 -0
  6. SoccerTwos/SoccerTwos-4999992.pt +3 -0
  7. SoccerTwos/SoccerTwos-5499977.onnx +3 -0
  8. SoccerTwos/SoccerTwos-5499977.pt +3 -0
  9. SoccerTwos/SoccerTwos-5999936.onnx +3 -0
  10. SoccerTwos/SoccerTwos-5999936.pt +3 -0
  11. SoccerTwos/SoccerTwos-6395296.onnx +3 -0
  12. SoccerTwos/SoccerTwos-6395296.pt +3 -0
  13. SoccerTwos/checkpoint.pt +3 -0
  14. SoccerTwos/events.out.tfevents.1684353327.mint1.73017.0 +3 -0
  15. config.json +1 -0
  16. configuration.yaml +82 -0
  17. run_logs/timers.json +424 -0
  18. run_logs/training_status.json +66 -0
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: Ktang2k/poca-SoccerTwos
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 sha256:4ee0ad0a9b3f5a7df303d024e3d327eef157f2e4f3e6153fcf67519d61aba4ed
3
+ size 1764633
SoccerTwos/SoccerTwos-4499899.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a19e4014b3953356d4dd806e8f0dbacc7d3f5e50695107daa6e46d47c253e04
3
+ size 1764633
SoccerTwos/SoccerTwos-4499899.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cb8202b35ad8d61fd8e3c58a6a797da626403dcb381ecc40083f0b179327e9
3
+ size 28422481
SoccerTwos/SoccerTwos-4999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52247475b41c3c051273d3741cb150bf92ee5b81fbe948559e29931f6f4caac
3
+ size 1764633
SoccerTwos/SoccerTwos-4999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848d30f514ebc5acff75d1e5b2783b5aba8a15c1d4bc862b3184bb0c13c4fc01
3
+ size 28422481
SoccerTwos/SoccerTwos-5499977.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40bcd394b6941a7c0517170e9fac0fcfaf7adcecd9da32b4df15aa3b8089d6f
3
+ size 1764633
SoccerTwos/SoccerTwos-5499977.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3cb55902944e7b0866418f9a82c8268a7099291dc604d709acc723a01609eb
3
+ size 28422481
SoccerTwos/SoccerTwos-5999936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7cc0b1b55834c3353b46aa105e1d930080c660528904da542ca6cdf05cc7c9a
3
+ size 1764633
SoccerTwos/SoccerTwos-5999936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c06f7a3809d29f31e099303ff619903f5730ee242afd85ee91d05eb830696c
3
+ size 28422481
SoccerTwos/SoccerTwos-6395296.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee0ad0a9b3f5a7df303d024e3d327eef157f2e4f3e6153fcf67519d61aba4ed
3
+ size 1764633
SoccerTwos/SoccerTwos-6395296.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f0667b5693ee03ffcfb64d102cfb3a49a8b34a08e589f0a38b25b8c5858d75
3
+ size 28422481
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f0667b5693ee03ffcfb64d102cfb3a49a8b34a08e589f0a38b25b8c5858d75
3
+ size 28422481
SoccerTwos/events.out.tfevents.1684353327.mint1.73017.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9b4c419b99e0cc578edca1fac9a5f060770ea5823bb0f0daf2bc2c0a62922f
3
+ size 6359963
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/linux/SoccerTwos/SoccerTwos", "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", "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 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/linux/SoccerTwos/SoccerTwos
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
73
+ initialize_from: null
74
+ load_model: false
75
+ resume: false
76
+ force: true
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 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 1.796678066253662,
6
+ "min": 1.6508715152740479,
7
+ "max": 3.2956461906433105,
8
+ "count": 639
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 35818.57421875,
12
+ "min": 30144.603515625,
13
+ "max": 113694.0,
14
+ "count": 639
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 58.654761904761905,
18
+ "min": 37.40769230769231,
19
+ "max": 999.0,
20
+ "count": 639
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 19708.0,
24
+ "min": 16716.0,
25
+ "max": 23924.0,
26
+ "count": 639
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1455.7522662230756,
30
+ "min": 1185.6997976068483,
31
+ "max": 1503.2913772759614,
32
+ "count": 631
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 244566.38072547672,
36
+ "min": 2372.8602712855063,
37
+ "max": 362195.66942273127,
38
+ "count": 631
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 6389884.0,
42
+ "min": 9982.0,
43
+ "max": 6389884.0,
44
+ "count": 639
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 6389884.0,
48
+ "min": 9982.0,
49
+ "max": 6389884.0,
50
+ "count": 639
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": -0.003226757748052478,
54
+ "min": -0.12121902406215668,
55
+ "max": 0.1877116858959198,
56
+ "count": 639
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": -0.5420953035354614,
60
+ "min": -28.00159454345703,
61
+ "max": 36.97920227050781,
62
+ "count": 639
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": -0.0032982449047267437,
66
+ "min": -0.12614789605140686,
67
+ "max": 0.1865699142217636,
68
+ "count": 639
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": -0.5541051626205444,
72
+ "min": -29.14016342163086,
73
+ "max": 36.7542724609375,
74
+ "count": 639
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 639
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 639
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.17651428637050448,
90
+ "min": -0.7869333326816559,
91
+ "max": 0.6341866610778703,
92
+ "count": 639
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 29.65440011024475,
96
+ "min": -54.91200006008148,
97
+ "max": 55.27120041847229,
98
+ "count": 639
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.17651428637050448,
102
+ "min": -0.7869333326816559,
103
+ "max": 0.6341866610778703,
104
+ "count": 639
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 29.65440011024475,
108
+ "min": -54.91200006008148,
109
+ "max": 55.27120041847229,
110
+ "count": 639
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 639
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 639
123
+ },
124
+ "SoccerTwos.Losses.PolicyLoss.mean": {
125
+ "value": 0.012226999139723678,
126
+ "min": 0.010700129181107817,
127
+ "max": 0.023625865237166484,
128
+ "count": 307
129
+ },
130
+ "SoccerTwos.Losses.PolicyLoss.sum": {
131
+ "value": 0.012226999139723678,
132
+ "min": 0.010700129181107817,
133
+ "max": 0.023625865237166484,
134
+ "count": 307
135
+ },
136
+ "SoccerTwos.Losses.ValueLoss.mean": {
137
+ "value": 0.10100149686137835,
138
+ "min": 0.00040658007201272995,
139
+ "max": 0.12078153441349665,
140
+ "count": 307
141
+ },
142
+ "SoccerTwos.Losses.ValueLoss.sum": {
143
+ "value": 0.10100149686137835,
144
+ "min": 0.00040658007201272995,
145
+ "max": 0.12078153441349665,
146
+ "count": 307
147
+ },
148
+ "SoccerTwos.Losses.BaselineLoss.mean": {
149
+ "value": 0.10279191260536512,
150
+ "min": 0.00039623022894375026,
151
+ "max": 0.1227528507510821,
152
+ "count": 307
153
+ },
154
+ "SoccerTwos.Losses.BaselineLoss.sum": {
155
+ "value": 0.10279191260536512,
156
+ "min": 0.00039623022894375026,
157
+ "max": 0.1227528507510821,
158
+ "count": 307
159
+ },
160
+ "SoccerTwos.Policy.LearningRate.mean": {
161
+ "value": 0.0003,
162
+ "min": 0.0003,
163
+ "max": 0.0003,
164
+ "count": 307
165
+ },
166
+ "SoccerTwos.Policy.LearningRate.sum": {
167
+ "value": 0.0003,
168
+ "min": 0.0003,
169
+ "max": 0.0003,
170
+ "count": 307
171
+ },
172
+ "SoccerTwos.Policy.Epsilon.mean": {
173
+ "value": 0.20000000000000007,
174
+ "min": 0.20000000000000007,
175
+ "max": 0.20000000000000007,
176
+ "count": 307
177
+ },
178
+ "SoccerTwos.Policy.Epsilon.sum": {
179
+ "value": 0.20000000000000007,
180
+ "min": 0.20000000000000007,
181
+ "max": 0.20000000000000007,
182
+ "count": 307
183
+ },
184
+ "SoccerTwos.Policy.Beta.mean": {
185
+ "value": 0.005000000000000001,
186
+ "min": 0.005000000000000001,
187
+ "max": 0.005000000000000001,
188
+ "count": 307
189
+ },
190
+ "SoccerTwos.Policy.Beta.sum": {
191
+ "value": 0.005000000000000001,
192
+ "min": 0.005000000000000001,
193
+ "max": 0.005000000000000001,
194
+ "count": 307
195
+ }
196
+ },
197
+ "metadata": {
198
+ "timer_format_version": "0.1.0",
199
+ "start_time_seconds": "1684353327",
200
+ "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
201
+ "command_line_arguments": "/home/kent/conda3/envs/rl-soccer2/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force",
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+cu102",
206
+ "numpy_version": "1.21.2",
207
+ "end_time_seconds": "1684362960"
208
+ },
209
+ "total": 9633.589431040004,
210
+ "count": 1,
211
+ "self": 0.0038056609919294715,
212
+ "children": {
213
+ "run_training.setup": {
214
+ "total": 0.007691809005336836,
215
+ "count": 1,
216
+ "self": 0.007691809005336836
217
+ },
218
+ "TrainerController.start_learning": {
219
+ "total": 9633.577933570006,
220
+ "count": 1,
221
+ "self": 6.980726071502431,
222
+ "children": {
223
+ "TrainerController._reset_env": {
224
+ "total": 2.5145168869494228,
225
+ "count": 32,
226
+ "self": 2.5145168869494228
227
+ },
228
+ "TrainerController.advance": {
229
+ "total": 9623.713544371552,
230
+ "count": 437536,
231
+ "self": 6.1688790749176405,
232
+ "children": {
233
+ "env_step": {
234
+ "total": 7378.757593222574,
235
+ "count": 437536,
236
+ "self": 6198.510448100147,
237
+ "children": {
238
+ "SubprocessEnvManager._take_step": {
239
+ "total": 1175.7724007374345,
240
+ "count": 437536,
241
+ "self": 32.29881483585632,
242
+ "children": {
243
+ "TorchPolicy.evaluate": {
244
+ "total": 1143.4735859015782,
245
+ "count": 807176,
246
+ "self": 1143.4735859015782
247
+ }
248
+ }
249
+ },
250
+ "workers": {
251
+ "total": 4.474744384991936,
252
+ "count": 437536,
253
+ "self": 0.0,
254
+ "children": {
255
+ "worker_root": {
256
+ "total": 9618.226115238416,
257
+ "count": 437536,
258
+ "is_parallel": true,
259
+ "self": 4240.423115636455,
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": 0.0034081870107911527,
269
+ "count": 2,
270
+ "is_parallel": true,
271
+ "self": 0.0005932310014031827,
272
+ "children": {
273
+ "_process_rank_one_or_two_observation": {
274
+ "total": 0.00281495600938797,
275
+ "count": 8,
276
+ "is_parallel": true,
277
+ "self": 0.00281495600938797
278
+ }
279
+ }
280
+ },
281
+ "UnityEnvironment.step": {
282
+ "total": 0.026518134996877052,
283
+ "count": 1,
284
+ "is_parallel": true,
285
+ "self": 0.0009760199900483713,
286
+ "children": {
287
+ "UnityEnvironment._generate_step_input": {
288
+ "total": 0.0006545910000568256,
289
+ "count": 1,
290
+ "is_parallel": true,
291
+ "self": 0.0006545910000568256
292
+ },
293
+ "communicator.exchange": {
294
+ "total": 0.022079807007685304,
295
+ "count": 1,
296
+ "is_parallel": true,
297
+ "self": 0.022079807007685304
298
+ },
299
+ "steps_from_proto": {
300
+ "total": 0.0028077169990865514,
301
+ "count": 2,
302
+ "is_parallel": true,
303
+ "self": 0.00042655297147575766,
304
+ "children": {
305
+ "_process_rank_one_or_two_observation": {
306
+ "total": 0.0023811640276107937,
307
+ "count": 8,
308
+ "is_parallel": true,
309
+ "self": 0.0023811640276107937
310
+ }
311
+ }
312
+ }
313
+ }
314
+ }
315
+ }
316
+ },
317
+ "UnityEnvironment.step": {
318
+ "total": 5377.716560485875,
319
+ "count": 437535,
320
+ "is_parallel": true,
321
+ "self": 389.5137392156612,
322
+ "children": {
323
+ "UnityEnvironment._generate_step_input": {
324
+ "total": 233.52408491376264,
325
+ "count": 437535,
326
+ "is_parallel": true,
327
+ "self": 233.52408491376264
328
+ },
329
+ "communicator.exchange": {
330
+ "total": 3662.8266292031767,
331
+ "count": 437535,
332
+ "is_parallel": true,
333
+ "self": 3662.8266292031767
334
+ },
335
+ "steps_from_proto": {
336
+ "total": 1091.8521071532741,
337
+ "count": 875070,
338
+ "is_parallel": true,
339
+ "self": 158.82564080308657,
340
+ "children": {
341
+ "_process_rank_one_or_two_observation": {
342
+ "total": 933.0264663501875,
343
+ "count": 3500280,
344
+ "is_parallel": true,
345
+ "self": 933.0264663501875
346
+ }
347
+ }
348
+ }
349
+ }
350
+ },
351
+ "steps_from_proto": {
352
+ "total": 0.08643911608669441,
353
+ "count": 62,
354
+ "is_parallel": true,
355
+ "self": 0.012416926969308406,
356
+ "children": {
357
+ "_process_rank_one_or_two_observation": {
358
+ "total": 0.074022189117386,
359
+ "count": 248,
360
+ "is_parallel": true,
361
+ "self": 0.074022189117386
362
+ }
363
+ }
364
+ }
365
+ }
366
+ }
367
+ }
368
+ }
369
+ }
370
+ },
371
+ "trainer_advance": {
372
+ "total": 2238.787072074061,
373
+ "count": 437536,
374
+ "self": 57.899110328624374,
375
+ "children": {
376
+ "process_trajectory": {
377
+ "total": 657.2002860603534,
378
+ "count": 437536,
379
+ "self": 654.284158256356,
380
+ "children": {
381
+ "RLTrainer._checkpoint": {
382
+ "total": 2.9161278039973695,
383
+ "count": 12,
384
+ "self": 2.9161278039973695
385
+ }
386
+ }
387
+ },
388
+ "_update_policy": {
389
+ "total": 1523.6876756850834,
390
+ "count": 308,
391
+ "self": 765.2689602988976,
392
+ "children": {
393
+ "TorchPOCAOptimizer.update": {
394
+ "total": 758.4187153861858,
395
+ "count": 9210,
396
+ "self": 758.4187153861858
397
+ }
398
+ }
399
+ }
400
+ }
401
+ }
402
+ }
403
+ },
404
+ "trainer_threads": {
405
+ "total": 7.899943739175797e-07,
406
+ "count": 1,
407
+ "self": 7.899943739175797e-07
408
+ },
409
+ "TrainerController._save_models": {
410
+ "total": 0.3691454500076361,
411
+ "count": 1,
412
+ "self": 0.0015013960073702037,
413
+ "children": {
414
+ "RLTrainer._checkpoint": {
415
+ "total": 0.3676440540002659,
416
+ "count": 1,
417
+ "self": 0.3676440540002659
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": 4499899,
6
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499899.onnx",
7
+ "reward": 0.0,
8
+ "creation_time": 1684360049.3053133,
9
+ "auxillary_file_paths": [
10
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-4499899.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 4999992,
15
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999992.onnx",
16
+ "reward": 0.0,
17
+ "creation_time": 1684360823.6323354,
18
+ "auxillary_file_paths": [
19
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-4999992.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 5499977,
24
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499977.onnx",
25
+ "reward": 0.0,
26
+ "creation_time": 1684361591.9752254,
27
+ "auxillary_file_paths": [
28
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-5499977.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 5999936,
33
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999936.onnx",
34
+ "reward": 0.0,
35
+ "creation_time": 1684362357.814007,
36
+ "auxillary_file_paths": [
37
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-5999936.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 6395296,
42
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6395296.onnx",
43
+ "reward": null,
44
+ "creation_time": 1684362960.0783129,
45
+ "auxillary_file_paths": [
46
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-6395296.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "elo": 1462.4165305123454,
51
+ "final_checkpoint": {
52
+ "steps": 6395296,
53
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
54
+ "reward": null,
55
+ "creation_time": 1684362960.0783129,
56
+ "auxillary_file_paths": [
57
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-6395296.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+cu102"
65
+ }
66
+ }