Hugging Face's logo

juan9
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
juan9 commited on
Commit
f668ff3
·
verified ·
1 Parent(s): 9708aff

First Push

Browse files
Files changed (5) hide show
  1. README.md +4 -4
  2. config.json +1 -1
  3. configuration.yaml +24 -11
  4. run_logs/timers.json +15 -345
  5. run_logs/training_status.json +0 -58
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
  library_name: ml-agents
3
  tags:
4
- - SnowballTarget
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
7
- - ML-Agents-SnowballTarget
8
  ---
9
 
10
- # **ppo** Agent playing **SnowballTarget**
11
- This is a trained model of a **ppo** agent playing **SnowballTarget**
12
  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
 
14
  ## Usage (with ML-Agents)
 
1
  ---
2
  library_name: ml-agents
3
  tags:
4
+ - Pyramids
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
7
+ - ML-Agents-Pyramids
8
  ---
9
 
10
+ # **ppo** Agent playing **Pyramids**
11
+ This is a trained model of a **ppo** agent playing **Pyramids**
12
  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
13
 
14
  ## Usage (with ML-Agents)
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids Training", "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 CHANGED
@@ -1,12 +1,12 @@
1
  default_settings: null
2
  behaviors:
3
- SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
- beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
  num_epoch: 3
@@ -14,10 +14,10 @@ behaviors:
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
- checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
- hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
@@ -35,17 +35,30 @@ behaviors:
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  init_path: null
39
- keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
- time_horizon: 64
43
- summary_freq: 10000
44
- threaded: true
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -66,7 +79,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
1
  default_settings: null
2
  behaviors:
3
+ Pyramids:
4
  trainer_type: ppo
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
+ beta: 0.01
10
  epsilon: 0.2
11
  lambd: 0.95
12
  num_epoch: 3
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 500000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 512
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
35
  memory: null
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
+ rnd:
39
+ gamma: 0.99
40
+ strength: 0.01
41
+ network_settings:
42
+ normalize: false
43
+ hidden_units: 64
44
+ num_layers: 3
45
+ vis_encode_type: simple
46
+ memory: null
47
+ goal_conditioning_type: hyper
48
+ deterministic: false
49
+ learning_rate: 0.0001
50
+ encoding_size: null
51
  init_path: null
52
+ keep_checkpoints: 5
53
  even_checkpoints: false
54
+ max_steps: 1000000
55
+ time_horizon: 128
56
+ summary_freq: 30000
57
+ threaded: false
58
  self_play: null
59
  behavioral_cloning: null
60
  env_settings:
61
+ env_path: ./training-envs-executables/linux/Pyramids/Pyramids
62
  env_args: null
63
  base_port: 5005
64
  num_envs: 1
 
79
  no_graphics_monitor: false
80
  environment_parameters: null
81
  checkpoint_settings:
82
+ run_id: Pyramids Training
83
  initialize_from: null
84
  load_model: false
85
  resume: false
run_logs/timers.json CHANGED
@@ -1,375 +1,45 @@
1
  {
2
  "name": "root",
3
- "gauges": {
4
- "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9914730787277222,
6
- "min": 0.9914730787277222,
7
- "max": 2.873957633972168,
8
- "count": 20
9
- },
10
- "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9499.3037109375,
12
- "min": 9499.3037109375,
13
- "max": 29495.427734375,
14
- "count": 20
15
- },
16
- "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
- },
22
- "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
- },
28
- "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.96503734588623,
30
- "min": 0.3656828999519348,
31
- "max": 12.96503734588623,
32
- "count": 20
33
- },
34
- "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2528.182373046875,
36
- "min": 70.9424819946289,
37
- "max": 2602.71875,
38
- "count": 20
39
- },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
- "count": 20
45
- },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
- "min": 8756.0,
49
- "max": 10945.0,
50
- "count": 20
51
- },
52
- "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06374345075849253,
54
- "min": 0.06169963288562476,
55
- "max": 0.07582122400430415,
56
- "count": 20
57
- },
58
- "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2549738030339701,
60
- "min": 0.24679853154249903,
61
- "max": 0.36523728684508516,
62
- "count": 20
63
- },
64
- "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20116959263881046,
66
- "min": 0.09848128757256941,
67
- "max": 0.2898164811525859,
68
- "count": 20
69
- },
70
- "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8046783705552418,
72
- "min": 0.39392515029027764,
73
- "max": 1.3678632022119035,
74
- "count": 20
75
- },
76
- "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
- },
82
- "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
- },
88
- "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
- },
94
- "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
- },
100
- "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
- "count": 20
105
- },
106
- "SnowballTarget.Policy.Beta.sum": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
- },
112
- "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.886363636363637,
114
- "min": 2.8636363636363638,
115
- "max": 25.886363636363637,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1139.0,
120
- "min": 126.0,
121
- "max": 1393.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.886363636363637,
126
- "min": 2.8636363636363638,
127
- "max": 25.886363636363637,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1139.0,
132
- "min": 126.0,
133
- "max": 1393.0,
134
- "count": 20
135
- },
136
- "SnowballTarget.IsTraining.mean": {
137
- "value": 1.0,
138
- "min": 1.0,
139
- "max": 1.0,
140
- "count": 20
141
- },
142
- "SnowballTarget.IsTraining.sum": {
143
- "value": 1.0,
144
- "min": 1.0,
145
- "max": 1.0,
146
- "count": 20
147
- }
148
- },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1707941657",
152
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.2.0+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1707942274"
160
  },
161
- "total": 616.9848276049999,
162
  "count": 1,
163
- "self": 0.5305121579997376,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.07121669399998609,
167
  "count": 1,
168
- "self": 0.07121669399998609
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 616.3830987530001,
172
  "count": 1,
173
- "self": 0.9253966029928051,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.86483831399994,
177
  "count": 1,
178
- "self": 4.86483831399994
179
- },
180
- "TrainerController.advance": {
181
- "total": 610.4914103100073,
182
- "count": 18203,
183
- "self": 0.44134618003295145,
184
- "children": {
185
- "env_step": {
186
- "total": 610.0500641299743,
187
- "count": 18203,
188
- "self": 469.4286792179771,
189
- "children": {
190
- "SubprocessEnvManager._take_step": {
191
- "total": 140.18064394098474,
192
- "count": 18203,
193
- "self": 2.7716976129713657,
194
- "children": {
195
- "TorchPolicy.evaluate": {
196
- "total": 137.40894632801337,
197
- "count": 18203,
198
- "self": 137.40894632801337
199
- }
200
- }
201
- },
202
- "workers": {
203
- "total": 0.4407409710124739,
204
- "count": 18203,
205
- "self": 0.0,
206
- "children": {
207
- "worker_root": {
208
- "total": 614.3191371800239,
209
- "count": 18203,
210
- "is_parallel": true,
211
- "self": 289.1690472830177,
212
- "children": {
213
- "run_training.setup": {
214
- "total": 0.0,
215
- "count": 0,
216
- "is_parallel": true,
217
- "self": 0.0,
218
- "children": {
219
- "steps_from_proto": {
220
- "total": 0.007789372000047479,
221
- "count": 1,
222
- "is_parallel": true,
223
- "self": 0.0055618820002791836,
224
- "children": {
225
- "_process_rank_one_or_two_observation": {
226
- "total": 0.002227489999768295,
227
- "count": 10,
228
- "is_parallel": true,
229
- "self": 0.002227489999768295
230
- }
231
- }
232
- },
233
- "UnityEnvironment.step": {
234
- "total": 0.05753250100008245,
235
- "count": 1,
236
- "is_parallel": true,
237
- "self": 0.0026428850000002058,
238
- "children": {
239
- "UnityEnvironment._generate_step_input": {
240
- "total": 0.0005031310000731537,
241
- "count": 1,
242
- "is_parallel": true,
243
- "self": 0.0005031310000731537
244
- },
245
- "communicator.exchange": {
246
- "total": 0.04731931200001327,
247
- "count": 1,
248
- "is_parallel": true,
249
- "self": 0.04731931200001327
250
- },
251
- "steps_from_proto": {
252
- "total": 0.007067172999995819,
253
- "count": 1,
254
- "is_parallel": true,
255
- "self": 0.0005673890000252868,
256
- "children": {
257
- "_process_rank_one_or_two_observation": {
258
- "total": 0.006499783999970532,
259
- "count": 10,
260
- "is_parallel": true,
261
- "self": 0.006499783999970532
262
- }
263
- }
264
- }
265
- }
266
- }
267
- }
268
- },
269
- "UnityEnvironment.step": {
270
- "total": 325.1500898970062,
271
- "count": 18202,
272
- "is_parallel": true,
273
- "self": 15.278682513998433,
274
- "children": {
275
- "UnityEnvironment._generate_step_input": {
276
- "total": 7.886213973984923,
277
- "count": 18202,
278
- "is_parallel": true,
279
- "self": 7.886213973984923
280
- },
281
- "communicator.exchange": {
282
- "total": 255.72345804001293,
283
- "count": 18202,
284
- "is_parallel": true,
285
- "self": 255.72345804001293
286
- },
287
- "steps_from_proto": {
288
- "total": 46.2617353690099,
289
- "count": 18202,
290
- "is_parallel": true,
291
- "self": 9.199899673961909,
292
- "children": {
293
- "_process_rank_one_or_two_observation": {
294
- "total": 37.06183569504799,
295
- "count": 182020,
296
- "is_parallel": true,
297
- "self": 37.06183569504799
298
- }
299
- }
300
- }
301
- }
302
- }
303
- }
304
- }
305
- }
306
- }
307
- }
308
- }
309
- }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00013422500001070148,
313
  "count": 1,
314
- "self": 0.00013422500001070148,
315
- "children": {
316
- "thread_root": {
317
- "total": 0.0,
318
- "count": 0,
319
- "is_parallel": true,
320
- "self": 0.0,
321
- "children": {
322
- "trainer_advance": {
323
- "total": 603.3576001671316,
324
- "count": 787096,
325
- "is_parallel": true,
326
- "self": 18.87754923110151,
327
- "children": {
328
- "process_trajectory": {
329
- "total": 321.9403706180301,
330
- "count": 787096,
331
- "is_parallel": true,
332
- "self": 321.37840758902985,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 0.5619630290002533,
336
- "count": 4,
337
- "is_parallel": true,
338
- "self": 0.5619630290002533
339
- }
340
- }
341
- },
342
- "_update_policy": {
343
- "total": 262.539680318,
344
- "count": 90,
345
- "is_parallel": true,
346
- "self": 68.92569046499761,
347
- "children": {
348
- "TorchPPOOptimizer.update": {
349
- "total": 193.6139898530024,
350
- "count": 4587,
351
- "is_parallel": true,
352
- "self": 193.6139898530024
353
- }
354
- }
355
- }
356
- }
357
- }
358
- }
359
- }
360
- }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.10131930100010322,
364
  "count": 1,
365
- "self": 0.0012558180001178698,
366
- "children": {
367
- "RLTrainer._checkpoint": {
368
- "total": 0.10006348299998535,
369
- "count": 1,
370
- "self": 0.10006348299998535
371
- }
372
- }
373
  }
374
  }
375
  }
 
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
+ "start_time_seconds": "1707941582",
6
  "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
7
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
8
  "mlagents_version": "1.1.0.dev0",
9
  "mlagents_envs_version": "1.1.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.2.0+cu121",
12
  "numpy_version": "1.23.5",
13
+ "end_time_seconds": "1707941582"
14
  },
15
+ "total": 0.1519914749999316,
16
  "count": 1,
17
+ "self": 0.016260902999988502,
18
  "children": {
19
  "run_training.setup": {
20
+ "total": 0.07344121500000256,
21
  "count": 1,
22
+ "self": 0.07344121500000256
23
  },
24
  "TrainerController.start_learning": {
25
+ "total": 0.06228935699994054,
26
  "count": 1,
27
+ "self": 0.0007777309999710269,
28
  "children": {
29
  "TrainerController._reset_env": {
30
+ "total": 0.06149067399996966,
31
  "count": 1,
32
+ "self": 0.06149067399996966
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
  "trainer_threads": {
35
+ "total": 1.2639999340535724e-06,
36
  "count": 1,
37
+ "self": 1.2639999340535724e-06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  },
39
  "TrainerController._save_models": {
40
+ "total": 1.9688000065798406e-05,
41
  "count": 1,
42
+ "self": 1.9688000065798406e-05
 
 
 
 
 
 
 
43
  }
44
  }
45
  }
run_logs/training_status.json CHANGED
@@ -1,62 +1,4 @@
1
  {
2
- "SnowballTarget": {
3
- "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.545454545454545,
8
- "creation_time": 1707941813.3585904,
9
- "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
- ]
12
- },
13
- {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 20.272727272727273,
17
- "creation_time": 1707941968.323758,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
- {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.727272727272727,
26
- "creation_time": 1707942119.6343586,
27
- "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
- ]
30
- },
31
- {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.272727272727273,
35
- "creation_time": 1707942273.4143367,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 25.272727272727273,
44
- "creation_time": 1707942273.5439253,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
- ]
48
- }
49
- ],
50
- "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.272727272727273,
54
- "creation_time": 1707942273.5439253,
55
- "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
- ]
58
- }
59
- },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.1.0.dev0",
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.1.0.dev0",