Hugging Face's logo

Niraya666
/
poca-SoccerTwos

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SoccerTwos
Model card Files Metrics Community
Niraya666 commited on
Commit
1c328cb
·
1 Parent(s): 7354d61

First Push

Browse files
Files changed (11) hide show
  1. README.md +31 -0
  2. SoccerTwos.onnx +3 -0
  3. SoccerTwos/SoccerTwos-25470.onnx +3 -0
  4. SoccerTwos/SoccerTwos-25470.pt +3 -0
  5. SoccerTwos/checkpoint.pt +3 -0
  6. SoccerTwos/events.out.tfevents.1678698702.LZYdeMacBook-Pro.local.6376.0 +3 -0
  7. config.json +1 -0
  8. configuration.yaml +82 -0
  9. run_logs/Player-0.log +51 -0
  10. run_logs/timers.json +289 -0
  11. run_logs/training_status.json +30 -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: Niraya666/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:a9328d032c9b873c85f9d262128599c092f7268ecb0ed17397a911783853e1c3
3
+ size 1764633
SoccerTwos/SoccerTwos-25470.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9328d032c9b873c85f9d262128599c092f7268ecb0ed17397a911783853e1c3
3
+ size 1764633
SoccerTwos/SoccerTwos-25470.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0808e5ab25578678e1d60c25c0acbe7ceb7d6262dad2fd9044c439b38a1b61b6
3
+ size 28421137
SoccerTwos/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0808e5ab25578678e1d60c25c0acbe7ceb7d6262dad2fd9044c439b38a1b61b6
3
+ size 28421137
SoccerTwos/events.out.tfevents.1678698702.LZYdeMacBook-Pro.local.6376.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4906c6ed7c3edd52e5b3d61282e03b934604b663dae6d89085cc22a60c1f5fe9
3
+ size 16734
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.app", "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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.app
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: false
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/Player-0.log ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Mono path[0] = '/Users/lzy/rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
2
+ Mono config path = '/Users/lzy/rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
3
+ New input system (experimental) initialized
4
+ Initialize engine version: 2021.3.17f1 (3e8111cac19d)
5
+ [Subsystems] Discovering subsystems at path /Users/lzy/rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/UnitySubsystems
6
+ GfxDevice: creating device client; threaded=1; jobified=0
7
+ preferred device: Apple M1 Pro (high power)
8
+ Metal devices available: 1
9
+ 0: Apple M1 Pro (high power)
10
+ Using device Apple M1 Pro (high power)
11
+ Initializing Metal device caps: Apple M1 Pro
12
+ Begin MonoManager ReloadAssembly
13
+ - Completed reload, in 0.144 seconds
14
+ UnloadTime: 1.563292 ms
15
+ Registered Communicator in Agent.
16
+ Setting up 5 worker threads for Enlighten.
17
+ Metal RecreateSurface[0x10d9f2680]: surface size 84x84
18
+ Metal RecreateSurface[0x10d9f2680]: surface size 640x820
19
+ Metal RecreateSurface[0x10d9f2680]: surface size 640x822
20
+ Metal RecreateSurface[0x10d9f2680]: surface size 648x850
21
+ Metal RecreateSurface[0x10d9f2680]: surface size 652x864
22
+ Metal RecreateSurface[0x10d9f2680]: surface size 652x866
23
+ Metal RecreateSurface[0x10d9f2680]: surface size 752x934
24
+ Metal RecreateSurface[0x10d9f2680]: surface size 802x966
25
+ Metal RecreateSurface[0x10d9f2680]: surface size 848x1004
26
+ Metal RecreateSurface[0x10d9f2680]: surface size 874x1034
27
+ Metal RecreateSurface[0x10d9f2680]: surface size 888x1050
28
+ Metal RecreateSurface[0x10d9f2680]: surface size 896x1060
29
+ Metal RecreateSurface[0x10d9f2680]: surface size 900x1066
30
+ Metal RecreateSurface[0x10d9f2680]: surface size 902x1070
31
+ Metal RecreateSurface[0x10d9f2680]: surface size 902x1068
32
+ Metal RecreateSurface[0x10d9f2680]: surface size 908x1078
33
+ Metal RecreateSurface[0x10d9f2680]: surface size 964x1134
34
+ Metal RecreateSurface[0x10d9f2680]: surface size 996x1160
35
+ Metal RecreateSurface[0x10d9f2680]: surface size 1026x1184
36
+ Metal RecreateSurface[0x10d9f2680]: surface size 1036x1192
37
+ TOO LONG
38
+ TOO LONG
39
+ TOO LONG
40
+ TOO LONG
41
+ TOO LONG
42
+ Metal RecreateSurface[0x10d9f2680]: surface size 1718x1192
43
+ Metal RecreateSurface[0x10d9f2680]: surface size 1804x1192
44
+ Metal RecreateSurface[0x10d9f2680]: surface size 1886x1192
45
+ Metal RecreateSurface[0x10d9f2680]: surface size 1918x1192
46
+ Metal RecreateSurface[0x10d9f2680]: surface size 1932x1192
47
+ Metal RecreateSurface[0x10d9f2680]: surface size 1934x1192
48
+ TOO LONG
49
+ TOO LONG
50
+ TOO LONG
51
+ TOO LONG
run_logs/timers.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name": "root",
3
+ "gauges": {
4
+ "SoccerTwos.Policy.Entropy.mean": {
5
+ "value": 3.2957346439361572,
6
+ "min": 3.2957346439361572,
7
+ "max": 3.2957401275634766,
8
+ "count": 2
9
+ },
10
+ "SoccerTwos.Policy.Entropy.sum": {
11
+ "value": 105463.5078125,
12
+ "min": 105463.5078125,
13
+ "max": 105463.6875,
14
+ "count": 2
15
+ },
16
+ "SoccerTwos.Environment.EpisodeLength.mean": {
17
+ "value": 848.5,
18
+ "min": 741.375,
19
+ "max": 848.5,
20
+ "count": 2
21
+ },
22
+ "SoccerTwos.Environment.EpisodeLength.sum": {
23
+ "value": 27152.0,
24
+ "min": 23724.0,
25
+ "max": 27152.0,
26
+ "count": 2
27
+ },
28
+ "SoccerTwos.Self-play.ELO.mean": {
29
+ "value": 1203.7074322323344,
30
+ "min": 1200.868917854648,
31
+ "max": 1203.7074322323344,
32
+ "count": 2
33
+ },
34
+ "SoccerTwos.Self-play.ELO.sum": {
35
+ "value": 7222.244593394007,
36
+ "min": 7222.244593394007,
37
+ "max": 9606.951342837185,
38
+ "count": 2
39
+ },
40
+ "SoccerTwos.Step.mean": {
41
+ "value": 19470.0,
42
+ "min": 9878.0,
43
+ "max": 19470.0,
44
+ "count": 2
45
+ },
46
+ "SoccerTwos.Step.sum": {
47
+ "value": 19470.0,
48
+ "min": 9878.0,
49
+ "max": 19470.0,
50
+ "count": 2
51
+ },
52
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
53
+ "value": 0.10651779174804688,
54
+ "min": 0.10651779174804688,
55
+ "max": 0.1065254807472229,
56
+ "count": 2
57
+ },
58
+ "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
59
+ "value": 1.2782135009765625,
60
+ "min": 1.2782135009765625,
61
+ "max": 1.4913567304611206,
62
+ "count": 2
63
+ },
64
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
65
+ "value": 0.10655638575553894,
66
+ "min": 0.10655638575553894,
67
+ "max": 0.10657714307308197,
68
+ "count": 2
69
+ },
70
+ "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
71
+ "value": 1.2786766290664673,
72
+ "min": 1.2786766290664673,
73
+ "max": 1.4920799732208252,
74
+ "count": 2
75
+ },
76
+ "SoccerTwos.Environment.CumulativeReward.mean": {
77
+ "value": 0.0,
78
+ "min": 0.0,
79
+ "max": 0.0,
80
+ "count": 2
81
+ },
82
+ "SoccerTwos.Environment.CumulativeReward.sum": {
83
+ "value": 0.0,
84
+ "min": 0.0,
85
+ "max": 0.0,
86
+ "count": 2
87
+ },
88
+ "SoccerTwos.Policy.ExtrinsicReward.mean": {
89
+ "value": 0.20076666648189226,
90
+ "min": 0.0604000056960753,
91
+ "max": 0.20076666648189226,
92
+ "count": 2
93
+ },
94
+ "SoccerTwos.Policy.ExtrinsicReward.sum": {
95
+ "value": 2.409199997782707,
96
+ "min": 0.8456000797450542,
97
+ "max": 2.409199997782707,
98
+ "count": 2
99
+ },
100
+ "SoccerTwos.Environment.GroupCumulativeReward.mean": {
101
+ "value": 0.20076666648189226,
102
+ "min": 0.0604000056960753,
103
+ "max": 0.20076666648189226,
104
+ "count": 2
105
+ },
106
+ "SoccerTwos.Environment.GroupCumulativeReward.sum": {
107
+ "value": 2.409199997782707,
108
+ "min": 0.8456000797450542,
109
+ "max": 2.409199997782707,
110
+ "count": 2
111
+ },
112
+ "SoccerTwos.IsTraining.mean": {
113
+ "value": 1.0,
114
+ "min": 1.0,
115
+ "max": 1.0,
116
+ "count": 2
117
+ },
118
+ "SoccerTwos.IsTraining.sum": {
119
+ "value": 1.0,
120
+ "min": 1.0,
121
+ "max": 1.0,
122
+ "count": 2
123
+ }
124
+ },
125
+ "metadata": {
126
+ "timer_format_version": "0.1.0",
127
+ "start_time_seconds": "1678698694",
128
+ "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]",
129
+ "command_line_arguments": "/Users/lzy/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --force",
130
+ "mlagents_version": "0.31.0.dev0",
131
+ "mlagents_envs_version": "0.31.0.dev0",
132
+ "communication_protocol_version": "1.5.0",
133
+ "pytorch_version": "1.11.0",
134
+ "numpy_version": "1.21.2",
135
+ "end_time_seconds": "1678698786"
136
+ },
137
+ "total": 92.23467170800001,
138
+ "count": 1,
139
+ "self": 0.003649750000008112,
140
+ "children": {
141
+ "run_training.setup": {
142
+ "total": 0.025393582999999942,
143
+ "count": 1,
144
+ "self": 0.025393582999999942
145
+ },
146
+ "TrainerController.start_learning": {
147
+ "total": 92.205628375,
148
+ "count": 1,
149
+ "self": 0.03839763100000937,
150
+ "children": {
151
+ "TrainerController._reset_env": {
152
+ "total": 7.957866083,
153
+ "count": 1,
154
+ "self": 7.957866083
155
+ },
156
+ "TrainerController.advance": {
157
+ "total": 84.07163257799998,
158
+ "count": 2005,
159
+ "self": 0.027443800999961354,
160
+ "children": {
161
+ "env_step": {
162
+ "total": 29.938097923000022,
163
+ "count": 2005,
164
+ "self": 24.28378593800024,
165
+ "children": {
166
+ "SubprocessEnvManager._take_step": {
167
+ "total": 5.635053451999944,
168
+ "count": 2005,
169
+ "self": 0.13653136800014565,
170
+ "children": {
171
+ "TorchPolicy.evaluate": {
172
+ "total": 5.498522083999799,
173
+ "count": 4000,
174
+ "self": 5.498522083999799
175
+ }
176
+ }
177
+ },
178
+ "workers": {
179
+ "total": 0.019258532999838707,
180
+ "count": 2005,
181
+ "self": 0.0,
182
+ "children": {
183
+ "worker_root": {
184
+ "total": 37.03397086699989,
185
+ "count": 2005,
186
+ "is_parallel": true,
187
+ "self": 16.108089045999847,
188
+ "children": {
189
+ "steps_from_proto": {
190
+ "total": 0.0034731670000009984,
191
+ "count": 2,
192
+ "is_parallel": true,
193
+ "self": 0.0004458740000021777,
194
+ "children": {
195
+ "_process_rank_one_or_two_observation": {
196
+ "total": 0.0030272929999988207,
197
+ "count": 8,
198
+ "is_parallel": true,
199
+ "self": 0.0030272929999988207
200
+ }
201
+ }
202
+ },
203
+ "UnityEnvironment.step": {
204
+ "total": 20.92240865400004,
205
+ "count": 2005,
206
+ "is_parallel": true,
207
+ "self": 0.8709159719997679,
208
+ "children": {
209
+ "UnityEnvironment._generate_step_input": {
210
+ "total": 0.5766720310000029,
211
+ "count": 2005,
212
+ "is_parallel": true,
213
+ "self": 0.5766720310000029
214
+ },
215
+ "communicator.exchange": {
216
+ "total": 16.695636735000186,
217
+ "count": 2005,
218
+ "is_parallel": true,
219
+ "self": 16.695636735000186
220
+ },
221
+ "steps_from_proto": {
222
+ "total": 2.779183916000086,
223
+ "count": 4010,
224
+ "is_parallel": true,
225
+ "self": 0.4580148530000052,
226
+ "children": {
227
+ "_process_rank_one_or_two_observation": {
228
+ "total": 2.321169063000081,
229
+ "count": 16040,
230
+ "is_parallel": true,
231
+ "self": 2.321169063000081
232
+ }
233
+ }
234
+ }
235
+ }
236
+ }
237
+ }
238
+ }
239
+ }
240
+ }
241
+ }
242
+ },
243
+ "trainer_advance": {
244
+ "total": 54.106090853999994,
245
+ "count": 2005,
246
+ "self": 0.15761011499999,
247
+ "children": {
248
+ "process_trajectory": {
249
+ "total": 9.034724489000013,
250
+ "count": 2005,
251
+ "self": 9.034724489000013
252
+ },
253
+ "_update_policy": {
254
+ "total": 44.91375624999999,
255
+ "count": 1,
256
+ "self": 1.858994246999977,
257
+ "children": {
258
+ "TorchPOCAOptimizer.update": {
259
+ "total": 43.054762003000015,
260
+ "count": 23,
261
+ "self": 43.054762003000015
262
+ }
263
+ }
264
+ }
265
+ }
266
+ }
267
+ }
268
+ },
269
+ "trainer_threads": {
270
+ "total": 1.250000011054908e-06,
271
+ "count": 1,
272
+ "self": 1.250000011054908e-06
273
+ },
274
+ "TrainerController._save_models": {
275
+ "total": 0.13773083300000621,
276
+ "count": 1,
277
+ "self": 0.0006390420000030872,
278
+ "children": {
279
+ "RLTrainer._checkpoint": {
280
+ "total": 0.13709179100000313,
281
+ "count": 1,
282
+ "self": 0.13709179100000313
283
+ }
284
+ }
285
+ }
286
+ }
287
+ }
288
+ }
289
+ }
run_logs/training_status.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "SoccerTwos": {
3
+ "elo": 1204.9301653200916,
4
+ "checkpoints": [
5
+ {
6
+ "steps": 25470,
7
+ "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-25470.onnx",
8
+ "reward": null,
9
+ "creation_time": 1678698786.8928761,
10
+ "auxillary_file_paths": [
11
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-25470.pt"
12
+ ]
13
+ }
14
+ ],
15
+ "final_checkpoint": {
16
+ "steps": 25470,
17
+ "file_path": "results/SoccerTwos/SoccerTwos.onnx",
18
+ "reward": null,
19
+ "creation_time": 1678698786.8928761,
20
+ "auxillary_file_paths": [
21
+ "results/SoccerTwos/SoccerTwos/SoccerTwos-25470.pt"
22
+ ]
23
+ }
24
+ },
25
+ "metadata": {
26
+ "stats_format_version": "0.3.0",
27
+ "mlagents_version": "0.31.0.dev0",
28
+ "torch_version": "1.11.0"
29
+ }
30
+ }