Hugging Face's logo

igpaub
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files Metrics Community
igpaub commited on
Commit
e9d7cb1
·
1 Parent(s): 105cf29

Huggy

Browse files
Files changed (21) hide show
  1. Huggy.onnx +1 -1
  2. Huggy/Huggy-4199974.onnx +3 -0
  3. Huggy/Huggy-4199974.pt +3 -0
  4. Huggy/Huggy-4399949.onnx +3 -0
  5. Huggy/Huggy-4399949.pt +3 -0
  6. Huggy/Huggy-4599929.onnx +3 -0
  7. Huggy/Huggy-4599929.pt +3 -0
  8. Huggy/Huggy-4799842.onnx +3 -0
  9. Huggy/Huggy-4799842.pt +3 -0
  10. Huggy/Huggy-4999924.onnx +3 -0
  11. Huggy/Huggy-4999924.pt +3 -0
  12. Huggy/Huggy-5000018.onnx +3 -0
  13. Huggy/Huggy-5000018.pt +3 -0
  14. Huggy/checkpoint.pt +1 -1
  15. Huggy/events.out.tfevents.1698755947.ba3352ddc336.34168.0 +3 -0
  16. Huggy/events.out.tfevents.1698755974.ba3352ddc336.34341.0 +3 -0
  17. config.json +1 -1
  18. configuration.yaml +3 -3
  19. run_logs/Player-0.log +14 -14
  20. run_logs/timers.json +168 -168
  21. run_logs/training_status.json +67 -67
Huggy.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a433bd5bfd2225e47c7f1785eab045e6cf8674693898034cfa2577e890cb9b96
3
  size 17134114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8430a03acce2da0d598260e3906dd3a20133c0cefb55e60e4ca84923cd51b1c7
3
  size 17134114
Huggy/Huggy-4199974.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49723175087839167cece74a05c9d544e63798c59d24f4ba6292da124b9a11eb
3
+ size 17134114
Huggy/Huggy-4199974.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b0a0ecd683cc9ac11156b2e21714e02aab637736626108e0e72563b2fb26c0
3
+ size 102546254
Huggy/Huggy-4399949.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e60f01d2d6564f249a1e6a521a0d41fce78fd27107315bdcf83b11bc3603595
3
+ size 17134114
Huggy/Huggy-4399949.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65a551ca2b2e3a6925359598ccb7fc306fa0d025ea4e516716b6f0bbcf795e8
3
+ size 102546254
Huggy/Huggy-4599929.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db525185fe7661bd1cf28e41ee3ab0aa95a9095e50aa5a3117f98769f15543b
3
+ size 17134114
Huggy/Huggy-4599929.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a79d2c8a697267e959a73ce1dda4ab8a50ad110bd85b38a2aa97912fa3e5ce
3
+ size 102546254
Huggy/Huggy-4799842.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be49ed4335abbc48f6f43fd8b93572b1793cd5c8c32b8c8cedb0358acc4edd8d
3
+ size 17134114
Huggy/Huggy-4799842.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae3a0e528b04aca25dd3e316c1677ed64eceb2e5dfbe4ee956992c5e4ea09a7
3
+ size 102546254
Huggy/Huggy-4999924.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a021a7df1ef21683e937ab001892de1b6ee1780fa750987333d1da194ba82620
3
+ size 17134114
Huggy/Huggy-4999924.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba5fdd421eacf609620ae85bd63f30263eb6f0564db38c2d0b5ee24953ef056
3
+ size 102546254
Huggy/Huggy-5000018.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8430a03acce2da0d598260e3906dd3a20133c0cefb55e60e4ca84923cd51b1c7
3
+ size 17134114
Huggy/Huggy-5000018.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73597242bbb16b920525be150bab025c09788b2e8757838bcadbbfecb6dc1777
3
+ size 102546254
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73f034ce095675d73032418af82d8e866e74dd3ec8e80e216342978cbf181e0b
3
  size 102545903
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da77d0f49f2e1e995a36637383574c27870236c0f9cf3a661ddca4c07e2810a4
3
  size 102545903
Huggy/events.out.tfevents.1698755947.ba3352ddc336.34168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7789c695744b03e16c6591ec4e5c236b5b990179a43fd79e6d22b30b4a284306
3
+ size 1123
Huggy/events.out.tfevents.1698755974.ba3352ddc336.34341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d0c5387ec5cf9bf1816381e279295c9a23042d0ab01823cf533394989701b7
3
+ size 105617
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "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": 200000, "network_settings": {"normalize": true, "hidden_units": 1024, "num_layers": 5, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 15, "even_checkpoints": false, "max_steps": 4000000, "time_horizon": 2000, "summary_freq": 100000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "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": 200000, "network_settings": {"normalize": true, "hidden_units": 1024, "num_layers": 5, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 15, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 2000, "summary_freq": 100000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "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 CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 15
40
  even_checkpoints: false
41
- max_steps: 4000000
42
  time_horizon: 2000
43
  summary_freq: 100000
44
  threaded: false
@@ -68,8 +68,8 @@ checkpoint_settings:
68
  run_id: Huggy
69
  initialize_from: null
70
  load_model: false
71
- resume: false
72
- force: true
73
  train_model: false
74
  inference: false
75
  results_dir: results
 
38
  init_path: null
39
  keep_checkpoints: 15
40
  even_checkpoints: false
41
+ max_steps: 5000000
42
  time_horizon: 2000
43
  summary_freq: 100000
44
  threaded: false
 
68
  run_id: Huggy
69
  initialize_from: null
70
  load_model: false
71
+ resume: true
72
+ force: false
73
  train_model: false
74
  inference: false
75
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.094 seconds
35
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -75,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
- UnloadTime: 0.647499 ms
79
  requesting resize 84 x 84
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
- Peak usage frame count: [4.0 KB-8.0 KB]: 53492 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
@@ -198,22 +198,22 @@ Memory Statistics:
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
- Peak main deferred allocation count 212
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
- Peak usage frame count: [16.0 MB-32.0 MB]: 53493 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
- Peak Allocated memory 25.1 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
- Peak usage frame count: [2.0 MB-4.0 MB]: 53493 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 2.6 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
@@ -242,13 +242,13 @@ Memory Statistics:
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
- Peak usage frame count: [32.0 KB-64.0 KB]: 53492 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
- Peak usage frame count: [64.0 KB-128.0 KB]: 53493 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
@@ -260,13 +260,13 @@ Memory Statistics:
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
- Peak usage frame count: [1.0 MB-2.0 MB]: 53492 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
- Peak usage frame count: [0.5 MB-1.0 MB]: 53492 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
@@ -278,13 +278,13 @@ Memory Statistics:
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
- Peak usage frame count: [0-1.0 KB]: 53493 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
- Peak usage frame count: [4.0 KB-8.0 KB]: 53493 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  Peak Allocated memory 7.3 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.081 seconds
35
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
75
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
76
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
77
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
78
+ UnloadTime: 0.639129 ms
79
  requesting resize 84 x 84
80
  Setting up 1 worker threads for Enlighten.
81
  Memory Statistics:
82
  [ALLOC_TEMP_TLS] TLS Allocator
83
  StackAllocators :
84
  [ALLOC_TEMP_MAIN]
85
+ Peak usage frame count: [4.0 KB-8.0 KB]: 13408 frames, [2.0 MB-4.0 MB]: 1 frames
86
  Initial Block Size 4.0 MB
87
  Current Block Size 4.0 MB
88
  Peak Allocated Bytes 3.6 MB
 
198
  Peak Allocated Bytes 0 B
199
  Overflow Count 0
200
  [ALLOC_DEFAULT] Dual Thread Allocator
201
+ Peak main deferred allocation count 306
202
  [ALLOC_BUCKET]
203
  Large Block size 4.0 MB
204
  Used Block count 1
205
  Peak Allocated bytes 1.4 MB
206
  [ALLOC_DEFAULT_MAIN]
207
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13409 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
+ Peak Allocated memory 23.0 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [2.0 MB-4.0 MB]: 13409 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 2.5 MB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_TEMP_JOB_1_FRAME]
219
  Initial Block Size 2.0 MB
 
242
  Used Block count 1
243
  Peak Allocated bytes 1.4 MB
244
  [ALLOC_GFX_MAIN]
245
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13408 frames, [64.0 KB-128.0 KB]: 1 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
  Peak Allocated memory 65.6 KB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_GFX_THREAD]
251
+ Peak usage frame count: [64.0 KB-128.0 KB]: 13409 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
  Peak Allocated memory 81.8 KB
 
260
  Used Block count 1
261
  Peak Allocated bytes 1.4 MB
262
  [ALLOC_CACHEOBJECTS_MAIN]
263
+ Peak usage frame count: [1.0 MB-2.0 MB]: 13408 frames, [16.0 MB-32.0 MB]: 1 frames
264
  Requested Block Size 4.0 MB
265
  Peak Block count 2
266
  Peak Allocated memory 30.6 MB
267
  Peak Large allocation bytes 24.9 MB
268
  [ALLOC_CACHEOBJECTS_THREAD]
269
+ Peak usage frame count: [0.5 MB-1.0 MB]: 13408 frames, [2.0 MB-4.0 MB]: 1 frames
270
  Requested Block Size 4.0 MB
271
  Peak Block count 1
272
  Peak Allocated memory 2.6 MB
 
278
  Used Block count 1
279
  Peak Allocated bytes 1.4 MB
280
  [ALLOC_TYPETREE_MAIN]
281
+ Peak usage frame count: [0-1.0 KB]: 13409 frames
282
  Requested Block Size 2.0 MB
283
  Peak Block count 1
284
  Peak Allocated memory 1.0 KB
285
  Peak Large allocation bytes 0 B
286
  [ALLOC_TYPETREE_THREAD]
287
+ Peak usage frame count: [4.0 KB-8.0 KB]: 13409 frames
288
  Requested Block Size 2.0 MB
289
  Peak Block count 1
290
  Peak Allocated memory 7.3 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
- "value": 1.3175311088562012,
6
- "min": 1.3175311088562012,
7
- "max": 1.418474555015564,
8
- "count": 40
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
- "value": 130278.796875,
12
- "min": 130278.796875,
13
- "max": 147496.71875,
14
- "count": 40
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
- "value": 133.07258064516128,
18
- "min": 85.9504347826087,
19
- "max": 377.07169811320756,
20
- "count": 40
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
- "value": 99006.0,
24
- "min": 98241.0,
25
- "max": 99924.0,
26
- "count": 40
27
  },
28
  "Huggy.Step.mean": {
29
- "value": 3999958.0,
30
- "min": 99860.0,
31
- "max": 3999958.0,
32
- "count": 40
33
  },
34
  "Huggy.Step.sum": {
35
- "value": 3999958.0,
36
- "min": 99860.0,
37
- "max": 3999958.0,
38
- "count": 40
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 2.2998576164245605,
42
- "min": 0.16505226492881775,
43
- "max": 2.4613800048828125,
44
- "count": 40
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 1711.093994140625,
48
- "min": 43.57379913330078,
49
- "max": 2814.1015625,
50
- "count": 40
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
- "value": 3.6141946537680525,
54
- "min": 2.311175460278085,
55
- "max": 3.969821947578454,
56
- "count": 40
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
- "value": 2688.960822403431,
60
- "min": 610.1503215134144,
61
- "max": 4531.147506177425,
62
- "count": 40
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
- "value": 3.6141946537680525,
66
- "min": 2.311175460278085,
67
- "max": 3.969821947578454,
68
- "count": 40
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
- "value": 2688.960822403431,
72
- "min": 610.1503215134144,
73
- "max": 4531.147506177425,
74
- "count": 40
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
- "value": 0.017417858828169604,
78
- "min": 0.014902591414477986,
79
- "max": 0.019508086560563243,
80
- "count": 40
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
- "value": 0.06967143531267841,
84
- "min": 0.061755724052394115,
85
- "max": 0.09488495137217494,
86
- "count": 40
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
- "value": 0.0329113794490695,
90
- "min": 0.02208210204417507,
91
- "max": 0.045109713276227315,
92
- "count": 40
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
- "value": 0.131645517796278,
96
- "min": 0.10259709749370813,
97
- "max": 0.22554856638113657,
98
- "count": 40
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
- "value": 3.851723716124996e-06,
102
- "min": 3.851723716124996e-06,
103
- "max": 0.00029612775129075,
104
- "count": 40
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
- "value": 1.5406894864499983e-05,
108
- "min": 1.5406894864499983e-05,
109
- "max": 0.0014456749681083497,
110
- "count": 40
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
- "value": 0.101283875,
114
- "min": 0.101283875,
115
- "max": 0.19870924999999995,
116
- "count": 40
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
- "value": 0.4051355,
120
- "min": 0.4051355,
121
- "max": 0.9818916500000001,
122
- "count": 40
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
- "value": 7.406536249999994e-05,
126
- "min": 7.406536249999994e-05,
127
- "max": 0.004935591575,
128
- "count": 40
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
- "value": 0.00029626144999999975,
132
- "min": 0.00029626144999999975,
133
- "max": 0.024096393334999997,
134
- "count": 40
135
  },
136
  "Huggy.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 40
141
  },
142
  "Huggy.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 40
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1698748991",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
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": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1698754354"
160
  },
161
- "total": 5362.90882316,
162
  "count": 1,
163
- "self": 0.8320937970001978,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.047339487000044755,
167
  "count": 1,
168
- "self": 0.047339487000044755
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 5362.029389876,
172
  "count": 1,
173
- "self": 9.432939677977629,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.368306509000149,
177
  "count": 1,
178
- "self": 3.368306509000149
179
  },
180
  "TrainerController.advance": {
181
- "total": 5348.244041902021,
182
- "count": 464503,
183
- "self": 10.107086691121367,
184
  "children": {
185
  "env_step": {
186
- "total": 4106.078288151914,
187
- "count": 464503,
188
- "self": 3315.8910334207458,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 783.9535560392383,
192
- "count": 464503,
193
- "self": 34.0685005553737,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 749.8850554838646,
197
- "count": 445774,
198
- "self": 749.8850554838646
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 6.233698691930158,
204
- "count": 464503,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 5345.166647694162,
209
- "count": 464503,
210
  "is_parallel": true,
211
- "self": 2649.367909529158,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
@@ -217,48 +217,48 @@
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.0008499460000166437,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0002486159999079973,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0006013300001086463,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.0006013300001086463
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.049959450999949695,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00029786700019940326,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00019118499994874583,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00019118499994874583
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04875125399985336,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04875125399985336
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0007191449999481847,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0001966339998489275,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0005225110000992572,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.0005225110000992572
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 2695.7987381650037,
271
- "count": 464502,
272
  "is_parallel": true,
273
- "self": 82.68031516074188,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 183.65110261324753,
277
- "count": 464502,
278
  "is_parallel": true,
279
- "self": 183.65110261324753
280
  },
281
  "communicator.exchange": {
282
- "total": 2239.7763229351312,
283
- "count": 464502,
284
  "is_parallel": true,
285
- "self": 2239.7763229351312
286
  },
287
  "steps_from_proto": {
288
- "total": 189.69099745588278,
289
- "count": 464502,
290
  "is_parallel": true,
291
- "self": 71.94834238865792,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 117.74265506722486,
295
- "count": 929004,
296
  "is_parallel": true,
297
- "self": 117.74265506722486
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 1232.0586670589853,
311
- "count": 464503,
312
- "self": 14.26233479698999,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 443.15114073899235,
316
- "count": 464503,
317
- "self": 340.4129772509916,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 102.73816348800074,
321
- "count": 20,
322
- "self": 102.73816348800074
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 774.645191523003,
328
- "count": 193,
329
- "self": 520.0062495090076,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 254.63894201399535,
333
- "count": 5790,
334
- "self": 254.63894201399535
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.1170004654559307e-06,
344
  "count": 1,
345
- "self": 1.1170004654559307e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.9841006700007711,
349
  "count": 1,
350
- "self": 0.026899033000518102,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.957201637000253,
354
  "count": 1,
355
- "self": 0.957201637000253
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.313913106918335,
6
+ "min": 1.313913106918335,
7
+ "max": 1.317245602607727,
8
+ "count": 10
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
+ "value": 130664.71875,
12
+ "min": 129024.421875,
13
+ "max": 134149.609375,
14
+ "count": 10
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 87.24889673433363,
18
+ "min": 65.08658294778586,
19
+ "max": 87.24889673433363,
20
+ "count": 10
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 98853.0,
24
+ "min": 98171.0,
25
+ "max": 99332.0,
26
+ "count": 10
27
  },
28
  "Huggy.Step.mean": {
29
+ "value": 4999924.0,
30
+ "min": 4099982.0,
31
+ "max": 4999924.0,
32
+ "count": 10
33
  },
34
  "Huggy.Step.sum": {
35
+ "value": 4999924.0,
36
+ "min": 4099982.0,
37
+ "max": 4999924.0,
38
+ "count": 10
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.4324426651000977,
42
+ "min": 2.4324426651000977,
43
+ "max": 2.5505118370056152,
44
+ "count": 10
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 2755.95751953125,
48
+ "min": 2755.95751953125,
49
+ "max": 3833.5390625,
50
+ "count": 10
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.8079658567852817,
54
+ "min": 3.8079658567852817,
55
+ "max": 4.05654823921314,
56
+ "count": 10
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 4314.425315737724,
60
+ "min": 4314.425315737724,
61
+ "max": 6065.738024711609,
62
+ "count": 10
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.8079658567852817,
66
+ "min": 3.8079658567852817,
67
+ "max": 4.05654823921314,
68
+ "count": 10
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 4314.425315737724,
72
+ "min": 4314.425315737724,
73
+ "max": 6065.738024711609,
74
+ "count": 10
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.014701851868497517,
78
+ "min": 0.014126381898283094,
79
+ "max": 0.018514142019800298,
80
+ "count": 10
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.07350925934248759,
84
+ "min": 0.056505527593132376,
85
+ "max": 0.09103437434144629,
86
+ "count": 10
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.046128600587447485,
90
+ "min": 0.04368286759903033,
91
+ "max": 0.061055387215067945,
92
+ "count": 10
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.23064300293723744,
96
+ "min": 0.184973868355155,
97
+ "max": 0.2889091414709886,
98
+ "count": 10
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
+ "value": 3.2159309280559994e-06,
102
+ "min": 3.2159309280559994e-06,
103
+ "max": 5.6923386025565e-05,
104
+ "count": 10
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
+ "value": 1.6079654640279996e-05,
108
+ "min": 1.6079654640279996e-05,
109
+ "max": 0.00025691765436091995,
110
+ "count": 10
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.10107194400000001,
114
+ "min": 0.10107194400000001,
115
+ "max": 0.11897443500000002,
116
+ "count": 10
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.5053597200000001,
120
+ "min": 0.41994962,
121
+ "max": 0.58563908,
122
+ "count": 10
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
+ "value": 6.349000560000001e-05,
126
+ "min": 6.349000560000001e-05,
127
+ "max": 0.0009568243065000003,
128
+ "count": 10
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
+ "value": 0.0003174500280000001,
132
+ "min": 0.0003174500280000001,
133
+ "max": 0.004323390092,
134
+ "count": 10
135
  },
136
  "Huggy.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 10
141
  },
142
  "Huggy.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1698755973",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
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": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1698757333"
160
  },
161
+ "total": 1359.5616869530004,
162
  "count": 1,
163
+ "self": 0.8612719400007336,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.044629289000113204,
167
  "count": 1,
168
+ "self": 0.044629289000113204
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1358.6557857239995,
172
  "count": 1,
173
+ "self": 2.4366720811076448,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.315022652999687,
177
  "count": 1,
178
+ "self": 4.315022652999687
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1350.7282377618922,
182
+ "count": 117824,
183
+ "self": 2.5804658236475007,
184
  "children": {
185
  "env_step": {
186
+ "total": 1042.6086795740512,
187
+ "count": 117824,
188
+ "self": 842.6668168675587,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 198.37702805137997,
192
+ "count": 117824,
193
+ "self": 8.648324341295847,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 189.72870371008412,
197
+ "count": 111736,
198
+ "self": 189.72870371008412
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.5648346551124632,
204
+ "count": 117824,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1348.1955729422607,
209
+ "count": 117824,
210
  "is_parallel": true,
211
+ "self": 665.3405499071905,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0008575070005463203,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0002671370002644835,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0005903700002818368,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0005903700002818368
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03037778299949423,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0002948659994217451,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00020318899987614714,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00020318899987614714
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.029165697999815166,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.029165697999815166
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0007140300003811717,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00020293600027798675,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.000511094000103185,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.000511094000103185
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 682.8550230350702,
271
+ "count": 117823,
272
  "is_parallel": true,
273
+ "self": 20.995316780616122,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 45.75232028135997,
277
+ "count": 117823,
278
  "is_parallel": true,
279
+ "self": 45.75232028135997
280
  },
281
  "communicator.exchange": {
282
+ "total": 568.0529631481322,
283
+ "count": 117823,
284
  "is_parallel": true,
285
+ "self": 568.0529631481322
286
  },
287
  "steps_from_proto": {
288
+ "total": 48.054422824961875,
289
+ "count": 117823,
290
  "is_parallel": true,
291
+ "self": 18.1666580222236,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 29.887764802738275,
295
+ "count": 235646,
296
  "is_parallel": true,
297
+ "self": 29.887764802738275
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 305.5390923641935,
311
+ "count": 117824,
312
+ "self": 3.3789918170332385,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 112.73238724916064,
316
+ "count": 117824,
317
+ "self": 94.71496339116038,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 18.017423858000257,
321
+ "count": 5,
322
+ "self": 18.017423858000257
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 189.42771329799962,
328
+ "count": 48,
329
+ "self": 126.5529493140175,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 62.87476398398212,
333
+ "count": 1440,
334
+ "self": 62.87476398398212
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.979994501918554e-07,
344
  "count": 1,
345
+ "self": 9.979994501918554e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 1.1758522300006007,
349
  "count": 1,
350
+ "self": 0.0316458520010201,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 1.1442063779995806,
354
  "count": 1,
355
+ "self": 1.1442063779995806
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,69 +1,6 @@
1
  {
2
  "Huggy": {
3
  "checkpoints": [
4
- {
5
- "steps": 1399782,
6
- "file_path": "results/Huggy/Huggy/Huggy-1399782.onnx",
7
- "reward": 1.8867632150650024,
8
- "creation_time": 1698750880.6251996,
9
- "auxillary_file_paths": [
10
- "results/Huggy/Huggy/Huggy-1399782.pt"
11
- ]
12
- },
13
- {
14
- "steps": 1599970,
15
- "file_path": "results/Huggy/Huggy/Huggy-1599970.onnx",
16
- "reward": 3.761632516882778,
17
- "creation_time": 1698751145.77036,
18
- "auxillary_file_paths": [
19
- "results/Huggy/Huggy/Huggy-1599970.pt"
20
- ]
21
- },
22
- {
23
- "steps": 1799986,
24
- "file_path": "results/Huggy/Huggy/Huggy-1799986.onnx",
25
- "reward": 3.6767572236061095,
26
- "creation_time": 1698751415.6137178,
27
- "auxillary_file_paths": [
28
- "results/Huggy/Huggy/Huggy-1799986.pt"
29
- ]
30
- },
31
- {
32
- "steps": 1999958,
33
- "file_path": "results/Huggy/Huggy/Huggy-1999958.onnx",
34
- "reward": 3.9970587723784976,
35
- "creation_time": 1698751684.4233077,
36
- "auxillary_file_paths": [
37
- "results/Huggy/Huggy/Huggy-1999958.pt"
38
- ]
39
- },
40
- {
41
- "steps": 2199963,
42
- "file_path": "results/Huggy/Huggy/Huggy-2199963.onnx",
43
- "reward": 3.7580735396007596,
44
- "creation_time": 1698751949.061678,
45
- "auxillary_file_paths": [
46
- "results/Huggy/Huggy/Huggy-2199963.pt"
47
- ]
48
- },
49
- {
50
- "steps": 2399875,
51
- "file_path": "results/Huggy/Huggy/Huggy-2399875.onnx",
52
- "reward": 3.9975703191012144,
53
- "creation_time": 1698752217.2232947,
54
- "auxillary_file_paths": [
55
- "results/Huggy/Huggy/Huggy-2399875.pt"
56
- ]
57
- },
58
- {
59
- "steps": 2599442,
60
- "file_path": "results/Huggy/Huggy/Huggy-2599442.onnx",
61
- "reward": 3.616936671733856,
62
- "creation_time": 1698752487.514141,
63
- "auxillary_file_paths": [
64
- "results/Huggy/Huggy/Huggy-2599442.pt"
65
- ]
66
- },
67
  {
68
  "steps": 2799900,
69
  "file_path": "results/Huggy/Huggy/Huggy-2799900.onnx",
@@ -135,15 +72,78 @@
135
  "auxillary_file_paths": [
136
  "results/Huggy/Huggy/Huggy-4000023.pt"
137
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
138
  }
139
  ],
140
  "final_checkpoint": {
141
- "steps": 4000023,
142
  "file_path": "results/Huggy/Huggy.onnx",
143
- "reward": 3.5867611978090173,
144
- "creation_time": 1698754353.3461125,
145
  "auxillary_file_paths": [
146
- "results/Huggy/Huggy/Huggy-4000023.pt"
147
  ]
148
  }
149
  },
 
1
  {
2
  "Huggy": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 2799900,
6
  "file_path": "results/Huggy/Huggy/Huggy-2799900.onnx",
 
72
  "auxillary_file_paths": [
73
  "results/Huggy/Huggy/Huggy-4000023.pt"
74
  ]
75
+ },
76
+ {
77
+ "steps": 4000023,
78
+ "file_path": "results/Huggy/Huggy/Huggy-4000023.onnx",
79
+ "reward": null,
80
+ "creation_time": 1698755957.437469,
81
+ "auxillary_file_paths": [
82
+ "results/Huggy/Huggy/Huggy-4000023.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 4199974,
87
+ "file_path": "results/Huggy/Huggy/Huggy-4199974.onnx",
88
+ "reward": 3.936265628784895,
89
+ "creation_time": 1698756253.7714355,
90
+ "auxillary_file_paths": [
91
+ "results/Huggy/Huggy/Huggy-4199974.pt"
92
+ ]
93
+ },
94
+ {
95
+ "steps": 4399949,
96
+ "file_path": "results/Huggy/Huggy/Huggy-4399949.onnx",
97
+ "reward": 3.821260338762532,
98
+ "creation_time": 1698756527.5513835,
99
+ "auxillary_file_paths": [
100
+ "results/Huggy/Huggy/Huggy-4399949.pt"
101
+ ]
102
+ },
103
+ {
104
+ "steps": 4599929,
105
+ "file_path": "results/Huggy/Huggy/Huggy-4599929.onnx",
106
+ "reward": 3.9875574823882847,
107
+ "creation_time": 1698756793.285191,
108
+ "auxillary_file_paths": [
109
+ "results/Huggy/Huggy/Huggy-4599929.pt"
110
+ ]
111
+ },
112
+ {
113
+ "steps": 4799842,
114
+ "file_path": "results/Huggy/Huggy/Huggy-4799842.onnx",
115
+ "reward": 3.78429541726818,
116
+ "creation_time": 1698757061.8041008,
117
+ "auxillary_file_paths": [
118
+ "results/Huggy/Huggy/Huggy-4799842.pt"
119
+ ]
120
+ },
121
+ {
122
+ "steps": 4999924,
123
+ "file_path": "results/Huggy/Huggy/Huggy-4999924.onnx",
124
+ "reward": 3.930067885089928,
125
+ "creation_time": 1698757331.4882176,
126
+ "auxillary_file_paths": [
127
+ "results/Huggy/Huggy/Huggy-4999924.pt"
128
+ ]
129
+ },
130
+ {
131
+ "steps": 5000018,
132
+ "file_path": "results/Huggy/Huggy/Huggy-5000018.onnx",
133
+ "reward": 3.952023536175281,
134
+ "creation_time": 1698757332.6298707,
135
+ "auxillary_file_paths": [
136
+ "results/Huggy/Huggy/Huggy-5000018.pt"
137
+ ]
138
  }
139
  ],
140
  "final_checkpoint": {
141
+ "steps": 5000018,
142
  "file_path": "results/Huggy/Huggy.onnx",
143
+ "reward": 3.952023536175281,
144
+ "creation_time": 1698757332.6298707,
145
  "auxillary_file_paths": [
146
+ "results/Huggy/Huggy/Huggy-5000018.pt"
147
  ]
148
  }
149
  },