Hugging Face's logo

yangchenx
/
ppo-Huggy

Reinforcement Learning
ml-agents
TensorBoard
ONNX
Huggy
deep-reinforcement-learning
ML-Agents-Huggy
Model card Files
xet
 Metrics Community
yangchenx commited on
Commit
2721b03
·
verified ·
1 Parent(s): 153b132

Huggy

Browse files
Files changed (16) hide show
  1. Huggy.onnx +1 -1
  2. Huggy/Huggy-1599936.onnx +3 -0
  3. Huggy/Huggy-1599936.pt +3 -0
  4. Huggy/Huggy-1799950.onnx +3 -0
  5. Huggy/Huggy-1799950.pt +3 -0
  6. Huggy/Huggy-1999919.onnx +3 -0
  7. Huggy/Huggy-1999919.pt +3 -0
  8. Huggy/Huggy-2000015.onnx +3 -0
  9. Huggy/Huggy-2000015.pt +3 -0
  10. Huggy/checkpoint.pt +1 -1
  11. Huggy/events.out.tfevents.1722513010.bd61de364e39.10822.0 +3 -0
  12. config.json +1 -1
  13. configuration.yaml +1 -1
  14. run_logs/Player-0.log +13 -16
  15. run_logs/timers.json +168 -168
  16. run_logs/training_status.json +40 -4
Huggy.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90045ffa82a48a12d866d509a9cc27caa5ad539e09a902869318ec7150dd17d3
3
  size 2273984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118ad13e35280176fc4fc582ed5cf7a62a7c1225cf5d45d6429fcd079a631a35
3
  size 2273984
Huggy/Huggy-1599936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8daa7dcc7f2fe9b65345c667d51d9a6abf53446fd7fce33a8e9ba076a196411a
3
+ size 2273984
Huggy/Huggy-1599936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543190d384b0442cfe53db9147db539313f3091020ad41b7d28dd873ec33dad2
3
+ size 13509473
Huggy/Huggy-1799950.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73bb608b31c6105a1ef943865e4c5bd02e468b21ddd00700b05184f6e303d9e4
3
+ size 2273984
Huggy/Huggy-1799950.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ce1a5181ea003c0db168097e547fa72ad30132ec8eca565217071dfeb9c96c
3
+ size 13509473
Huggy/Huggy-1999919.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae89d55cd49acb4333fb7934fbea44ac0047edaa5d28944598f53cdf229427f
3
+ size 2273984
Huggy/Huggy-1999919.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05239a28092ad57d58b454534bb866d25f806a795408ae41a587a57e4888f141
3
+ size 13509473
Huggy/Huggy-2000015.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118ad13e35280176fc4fc582ed5cf7a62a7c1225cf5d45d6429fcd079a631a35
3
+ size 2273984
Huggy/Huggy-2000015.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c250c1b3f66736bc2e3ebee4376a31d1cb46452397c69f949d1f153d493ec785
3
+ size 13509473
Huggy/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e1ed0b9f387eebd65adf24fefef85a5f2eb4d703cd443bb2e11782dd6177ec9
3
  size 13509218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad3189d0d16b1c1104c414c1a6e4c911643bbcaa203dc3e9469391ff2f8bae7
3
  size 13509218
Huggy/events.out.tfevents.1722513010.bd61de364e39.10822.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607c22d8395a500b15643d6b0776bf14cff72892912073da1c8209bc74dff91a
3
+ size 119297
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": 512, "num_layers": 3, "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": 2000000, "time_horizon": 1000, "summary_freq": 50000, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "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": {"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": 512, "num_layers": 3, "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": 2000000, "time_horizon": 1000, "summary_freq": 50000, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "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
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: Huggy2
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
69
  run_id: Huggy2
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
2
  Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.090 seconds
38
  ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
78
  WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
79
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
80
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
81
- UnloadTime: 1.116764 ms
82
  requesting resize 84 x 84
83
  Setting up 1 worker threads for Enlighten.
84
  Memory Statistics:
85
  [ALLOC_TEMP_TLS] TLS Allocator
86
  StackAllocators :
87
  [ALLOC_TEMP_MAIN]
88
- Peak usage frame count: [4.0 KB-8.0 KB]: 18774 frames, [2.0 MB-4.0 MB]: 1 frames
89
  Initial Block Size 4.0 MB
90
  Current Block Size 4.0 MB
91
  Peak Allocated Bytes 3.6 MB
@@ -93,7 +90,7 @@ Memory Statistics:
93
  [ALLOC_TEMP_Loading.AsyncRead]
94
  Initial Block Size 64.0 KB
95
  Current Block Size 64.0 KB
96
- Peak Allocated Bytes 184 B
97
  Overflow Count 0
98
  [ALLOC_TEMP_Loading.PreloadManager]
99
  Initial Block Size 256.0 KB
@@ -207,13 +204,13 @@ Memory Statistics:
207
  Used Block count 1
208
  Peak Allocated bytes 1.4 MB
209
  [ALLOC_DEFAULT_MAIN]
210
- Peak usage frame count: [16.0 MB-32.0 MB]: 18775 frames
211
  Requested Block Size 16.0 MB
212
  Peak Block count 1
213
- Peak Allocated memory 22.6 MB
214
  Peak Large allocation bytes 16.0 MB
215
  [ALLOC_DEFAULT_THREAD]
216
- Peak usage frame count: [2.0 MB-4.0 MB]: 18775 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 2.5 MB
@@ -245,13 +242,13 @@ Memory Statistics:
245
  Used Block count 1
246
  Peak Allocated bytes 1.4 MB
247
  [ALLOC_GFX_MAIN]
248
- Peak usage frame count: [32.0 KB-64.0 KB]: 18774 frames, [64.0 KB-128.0 KB]: 1 frames
249
  Requested Block Size 16.0 MB
250
  Peak Block count 1
251
  Peak Allocated memory 65.6 KB
252
  Peak Large allocation bytes 0 B
253
  [ALLOC_GFX_THREAD]
254
- Peak usage frame count: [64.0 KB-128.0 KB]: 18775 frames
255
  Requested Block Size 16.0 MB
256
  Peak Block count 1
257
  Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
263
  Used Block count 1
264
  Peak Allocated bytes 1.4 MB
265
  [ALLOC_CACHEOBJECTS_MAIN]
266
- Peak usage frame count: [1.0 MB-2.0 MB]: 18774 frames, [16.0 MB-32.0 MB]: 1 frames
267
  Requested Block Size 4.0 MB
268
  Peak Block count 2
269
  Peak Allocated memory 30.6 MB
270
  Peak Large allocation bytes 24.9 MB
271
  [ALLOC_CACHEOBJECTS_THREAD]
272
- Peak usage frame count: [0.5 MB-1.0 MB]: 18774 frames, [2.0 MB-4.0 MB]: 1 frames
273
  Requested Block Size 4.0 MB
274
  Peak Block count 1
275
  Peak Allocated memory 2.6 MB
@@ -281,13 +278,13 @@ Memory Statistics:
281
  Used Block count 1
282
  Peak Allocated bytes 1.4 MB
283
  [ALLOC_TYPETREE_MAIN]
284
- Peak usage frame count: [0-1.0 KB]: 18775 frames
285
  Requested Block Size 2.0 MB
286
  Peak Block count 1
287
  Peak Allocated memory 1.0 KB
288
  Peak Large allocation bytes 0 B
289
  [ALLOC_TYPETREE_THREAD]
290
- Peak usage frame count: [4.0 KB-8.0 KB]: 18775 frames
291
  Requested Block Size 2.0 MB
292
  Peak Block count 1
293
  Peak Allocated memory 7.3 KB
 
2
  Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
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 0.093 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: 0.742892 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]: 8024 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
 
90
  [ALLOC_TEMP_Loading.AsyncRead]
91
  Initial Block Size 64.0 KB
92
  Current Block Size 64.0 KB
93
+ Peak Allocated Bytes 160 B
94
  Overflow Count 0
95
  [ALLOC_TEMP_Loading.PreloadManager]
96
  Initial Block Size 256.0 KB
 
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]: 8025 frames
208
  Requested Block Size 16.0 MB
209
  Peak Block count 1
210
+ Peak Allocated memory 22.3 MB
211
  Peak Large allocation bytes 16.0 MB
212
  [ALLOC_DEFAULT_THREAD]
213
+ Peak usage frame count: [2.0 MB-4.0 MB]: 8025 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 2.5 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]: 8024 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]: 8025 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]: 8024 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]: 8024 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]: 8025 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]: 8025 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": 1.4091967344284058,
6
- "min": 1.4091967344284058,
7
- "max": 1.4266935586929321,
8
- "count": 28
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
- "value": 71195.4375,
12
- "min": 68479.0859375,
13
- "max": 77438.2421875,
14
- "count": 28
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
- "value": 102.4074844074844,
18
- "min": 93.96768060836501,
19
- "max": 390.6953125,
20
- "count": 28
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
- "value": 49258.0,
24
- "min": 48879.0,
25
- "max": 50227.0,
26
- "count": 28
27
  },
28
  "Huggy.Step.mean": {
29
- "value": 1399995.0,
30
- "min": 49929.0,
31
- "max": 1399995.0,
32
- "count": 28
33
  },
34
  "Huggy.Step.sum": {
35
- "value": 1399995.0,
36
- "min": 49929.0,
37
- "max": 1399995.0,
38
- "count": 28
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
- "value": 2.3200318813323975,
42
- "min": 0.10346867889165878,
43
- "max": 2.3808159828186035,
44
- "count": 28
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
- "value": 1115.935302734375,
48
- "min": 13.140522003173828,
49
- "max": 1219.5640869140625,
50
- "count": 28
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
- "value": 3.695439128518848,
54
- "min": 1.7290600467854598,
55
- "max": 3.8776435249126875,
56
- "count": 28
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
- "value": 1777.506220817566,
60
- "min": 219.5906259417534,
61
- "max": 2016.3746329545975,
62
- "count": 28
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
- "value": 3.695439128518848,
66
- "min": 1.7290600467854598,
67
- "max": 3.8776435249126875,
68
- "count": 28
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
- "value": 1777.506220817566,
72
- "min": 219.5906259417534,
73
- "max": 2016.3746329545975,
74
- "count": 28
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
- "value": 0.014578134174765486,
78
- "min": 0.014578134174765486,
79
- "max": 0.020176267295513146,
80
- "count": 28
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
- "value": 0.029156268349530973,
84
- "min": 0.029156268349530973,
85
- "max": 0.056400772003204716,
86
- "count": 28
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
- "value": 0.04598704297095538,
90
- "min": 0.022827260341081356,
91
- "max": 0.05807238076296117,
92
- "count": 28
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
- "value": 0.09197408594191075,
96
- "min": 0.046361254838605724,
97
- "max": 0.17421714228888352,
98
- "count": 28
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
- "value": 9.438096853970002e-05,
102
- "min": 9.438096853970002e-05,
103
- "max": 0.0002953029765656749,
104
- "count": 28
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
- "value": 0.00018876193707940004,
108
- "min": 0.00018876193707940004,
109
- "max": 0.0008439820686726498,
110
- "count": 28
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
- "value": 0.13146029999999997,
114
- "min": 0.13146029999999997,
115
- "max": 0.19843432500000002,
116
- "count": 28
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
- "value": 0.26292059999999995,
120
- "min": 0.26292059999999995,
121
- "max": 0.5813273499999999,
122
- "count": 28
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
- "value": 0.00157986897,
126
- "min": 0.00157986897,
127
- "max": 0.004921872817500001,
128
- "count": 28
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
- "value": 0.00315973794,
132
- "min": 0.00315973794,
133
- "max": 0.014068234765000003,
134
- "count": 28
135
  },
136
  "Huggy.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 28
141
  },
142
  "Huggy.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 28
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1722511118",
152
  "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=Huggy2 --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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1722512755"
160
  },
161
- "total": 1637.6247964059999,
162
  "count": 1,
163
- "self": 0.46097642299992003,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.0627545590000409,
167
  "count": 1,
168
- "self": 0.0627545590000409
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 1637.101065424,
172
  "count": 1,
173
- "self": 3.009166965059194,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.01938407800003,
177
  "count": 1,
178
- "self": 3.01938407800003
179
  },
180
  "TrainerController.advance": {
181
- "total": 1630.8104392789407,
182
- "count": 162057,
183
- "self": 3.1447474499498185,
184
  "children": {
185
  "env_step": {
186
- "total": 1290.7198713769653,
187
- "count": 162057,
188
- "self": 1062.53743337192,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 226.26409632901914,
192
- "count": 162057,
193
- "self": 11.987310262985261,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 214.27678606603388,
197
- "count": 156459,
198
- "self": 214.27678606603388
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 1.9183416760259888,
204
- "count": 162056,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 1631.9033727829997,
209
- "count": 162056,
210
  "is_parallel": true,
211
- "self": 774.5841785009446,
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": 0.0010182760000816415,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00023217800014663226,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0007860979999350093,
227
  "count": 2,
228
  "is_parallel": true,
229
- "self": 0.0007860979999350093
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.028593586000056348,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0003738259999863658,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00023898400002053677,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00023898400002053677
244
  },
245
  "communicator.exchange": {
246
- "total": 0.02721304700003202,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.02721304700003202
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0007677290000174253,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00019002499993803212,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0005777040000793932,
259
  "count": 2,
260
  "is_parallel": true,
261
- "self": 0.0005777040000793932
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 857.319194282055,
271
- "count": 162055,
272
  "is_parallel": true,
273
- "self": 26.156277106039852,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 55.2540211049826,
277
- "count": 162055,
278
  "is_parallel": true,
279
- "self": 55.2540211049826
280
  },
281
  "communicator.exchange": {
282
- "total": 714.4132618270073,
283
- "count": 162055,
284
  "is_parallel": true,
285
- "self": 714.4132618270073
286
  },
287
  "steps_from_proto": {
288
- "total": 61.49563424402527,
289
- "count": 162055,
290
  "is_parallel": true,
291
- "self": 21.616702721090633,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 39.878931522934636,
295
- "count": 324110,
296
  "is_parallel": true,
297
- "self": 39.878931522934636
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 336.9458204520255,
311
- "count": 162056,
312
- "self": 4.558569886025452,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 99.59555762599928,
316
- "count": 162056,
317
- "self": 98.69312244199944,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.9024351839998417,
321
- "count": 7,
322
- "self": 0.9024351839998417
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 232.79169294000076,
328
- "count": 68,
329
- "self": 188.07634617599808,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 44.715346764002675,
333
- "count": 2040,
334
- "self": 44.715346764002675
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.3809999472869094e-06,
344
  "count": 1,
345
- "self": 1.3809999472869094e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.26207372099997883,
349
  "count": 1,
350
- "self": 0.003281280000010156,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.2587924409999687,
354
  "count": 1,
355
- "self": 0.2587924409999687
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "Huggy.Policy.Entropy.mean": {
5
+ "value": 1.4055622816085815,
6
+ "min": 1.4055622816085815,
7
+ "max": 1.4085252285003662,
8
+ "count": 12
9
  },
10
  "Huggy.Policy.Entropy.sum": {
11
+ "value": 69707.453125,
12
+ "min": 69093.796875,
13
+ "max": 71867.4453125,
14
+ "count": 12
15
  },
16
  "Huggy.Environment.EpisodeLength.mean": {
17
+ "value": 92.3177570093458,
18
+ "min": 76.66074313408724,
19
+ "max": 92.3177570093458,
20
+ "count": 12
21
  },
22
  "Huggy.Environment.EpisodeLength.sum": {
23
+ "value": 49390.0,
24
+ "min": 47453.0,
25
+ "max": 49481.0,
26
+ "count": 12
27
  },
28
  "Huggy.Step.mean": {
29
+ "value": 1999919.0,
30
+ "min": 1449956.0,
31
+ "max": 1999919.0,
32
+ "count": 12
33
  },
34
  "Huggy.Step.sum": {
35
+ "value": 1999919.0,
36
+ "min": 1449956.0,
37
+ "max": 1999919.0,
38
+ "count": 12
39
  },
40
  "Huggy.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.3376569747924805,
42
+ "min": 2.3376569747924805,
43
+ "max": 2.426429271697998,
44
+ "count": 12
45
  },
46
  "Huggy.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 1250.646484375,
48
+ "min": 1250.646484375,
49
+ "max": 1529.655029296875,
50
+ "count": 12
51
  },
52
  "Huggy.Environment.CumulativeReward.mean": {
53
+ "value": 3.6791030330078622,
54
+ "min": 3.6791030330078622,
55
+ "max": 4.011462597008174,
56
+ "count": 12
57
  },
58
  "Huggy.Environment.CumulativeReward.sum": {
59
+ "value": 1968.3201226592064,
60
+ "min": 1968.3201226592064,
61
+ "max": 2531.232898712158,
62
+ "count": 12
63
  },
64
  "Huggy.Policy.ExtrinsicReward.mean": {
65
+ "value": 3.6791030330078622,
66
+ "min": 3.6791030330078622,
67
+ "max": 4.011462597008174,
68
+ "count": 12
69
  },
70
  "Huggy.Policy.ExtrinsicReward.sum": {
71
+ "value": 1968.3201226592064,
72
+ "min": 1968.3201226592064,
73
+ "max": 2531.232898712158,
74
+ "count": 12
75
  },
76
  "Huggy.Losses.PolicyLoss.mean": {
77
+ "value": 0.013913452498672997,
78
+ "min": 0.013913452498672997,
79
+ "max": 0.021045668007961163,
80
+ "count": 12
81
  },
82
  "Huggy.Losses.PolicyLoss.sum": {
83
+ "value": 0.04174035749601899,
84
+ "min": 0.03015493310595048,
85
+ "max": 0.05919787979898199,
86
+ "count": 12
87
  },
88
  "Huggy.Losses.ValueLoss.mean": {
89
+ "value": 0.06033656601276663,
90
+ "min": 0.05310322812034024,
91
+ "max": 0.07016664296388626,
92
+ "count": 12
93
  },
94
  "Huggy.Losses.ValueLoss.sum": {
95
+ "value": 0.1810096980382999,
96
+ "min": 0.10750966668128967,
97
+ "max": 0.1810096980382999,
98
+ "count": 12
99
  },
100
  "Huggy.Policy.LearningRate.mean": {
101
+ "value": 3.2819489060499966e-06,
102
+ "min": 3.2819489060499966e-06,
103
+ "max": 8.508772163745001e-05,
104
+ "count": 12
105
  },
106
  "Huggy.Policy.LearningRate.sum": {
107
+ "value": 9.84584671814999e-06,
108
+ "min": 9.84584671814999e-06,
109
+ "max": 0.00021373417875535,
110
+ "count": 12
111
  },
112
  "Huggy.Policy.Epsilon.mean": {
113
+ "value": 0.10109394999999999,
114
+ "min": 0.10109394999999999,
115
+ "max": 0.12836255000000002,
116
+ "count": 12
117
  },
118
  "Huggy.Policy.Epsilon.sum": {
119
+ "value": 0.30328184999999996,
120
+ "min": 0.2073907000000001,
121
+ "max": 0.37124465,
122
+ "count": 12
123
  },
124
  "Huggy.Policy.Beta.mean": {
125
+ "value": 6.458810499999997e-05,
126
+ "min": 6.458810499999997e-05,
127
+ "max": 0.0014252912449999996,
128
+ "count": 12
129
  },
130
  "Huggy.Policy.Beta.sum": {
131
+ "value": 0.0001937643149999999,
132
+ "min": 0.0001937643149999999,
133
+ "max": 0.0035851080350000003,
134
+ "count": 12
135
  },
136
  "Huggy.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 12
141
  },
142
  "Huggy.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 12
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1722513009",
152
  "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=Huggy2 --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": "2.3.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1722513719"
160
  },
161
+ "total": 710.168198028,
162
  "count": 1,
163
+ "self": 0.436551648999739,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.054785497000011674,
167
  "count": 1,
168
+ "self": 0.054785497000011674
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 709.6768608820003,
172
  "count": 1,
173
+ "self": 1.3114471539533952,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.1492431080000642,
177
  "count": 1,
178
+ "self": 2.1492431080000642
179
  },
180
  "TrainerController.advance": {
181
+ "total": 706.101217920047,
182
+ "count": 70369,
183
+ "self": 1.3735956280947903,
184
  "children": {
185
  "env_step": {
186
+ "total": 553.4422669140436,
187
+ "count": 70369,
188
+ "self": 458.46712625608916,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 94.15870611399168,
192
+ "count": 70369,
193
+ "self": 4.684341862015572,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 89.47436425197611,
197
+ "count": 66869,
198
+ "self": 89.47436425197611
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.8164345439627141,
204
+ "count": 70369,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 707.3437201060142,
209
+ "count": 70369,
210
  "is_parallel": true,
211
+ "self": 335.0738939629914,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0009061069999916072,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0002663190002749616,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0006397879997166456,
227
  "count": 2,
228
  "is_parallel": true,
229
+ "self": 0.0006397879997166456
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.030327748999752657,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0003858850000142411,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00020546299992929562,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00020546299992929562
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.02896766399999251,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.02896766399999251
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0007687369998166105,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00020107599993934855,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005676609998772619,
259
  "count": 2,
260
  "is_parallel": true,
261
+ "self": 0.0005676609998772619
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 372.2698261430228,
271
+ "count": 70368,
272
  "is_parallel": true,
273
+ "self": 11.275880513054744,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 23.658077269045407,
277
+ "count": 70368,
278
  "is_parallel": true,
279
+ "self": 23.658077269045407
280
  },
281
  "communicator.exchange": {
282
+ "total": 310.9559756269923,
283
+ "count": 70368,
284
  "is_parallel": true,
285
+ "self": 310.9559756269923
286
  },
287
  "steps_from_proto": {
288
+ "total": 26.37989273393032,
289
+ "count": 70368,
290
  "is_parallel": true,
291
+ "self": 9.36228497688171,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 17.01760775704861,
295
+ "count": 140736,
296
  "is_parallel": true,
297
+ "self": 17.01760775704861
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 151.28535537790867,
311
+ "count": 70369,
312
+ "self": 1.925617109936411,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 50.56208818397181,
316
+ "count": 70369,
317
+ "self": 50.202114165972034,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.35997401799977524,
321
+ "count": 3,
322
+ "self": 0.35997401799977524
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 98.79765008400045,
328
+ "count": 29,
329
+ "self": 79.461304319997,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 19.336345764003454,
333
+ "count": 870,
334
+ "self": 19.336345764003454
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.099999260797631e-07,
344
  "count": 1,
345
+ "self": 9.099999260797631e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.11495178999985001,
349
  "count": 1,
350
+ "self": 0.0030589199996029492,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.11189287000024706,
354
  "count": 1,
355
+ "self": 0.11189287000024706
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -72,15 +72,51 @@
72
  "auxillary_file_paths": [
73
  "results/Huggy2/Huggy/Huggy-1401988.pt"
74
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
  "final_checkpoint": {
78
- "steps": 1401988,
79
  "file_path": "results/Huggy2/Huggy.onnx",
80
- "reward": 3.904681622982025,
81
- "creation_time": 1722512755.2275996,
82
  "auxillary_file_paths": [
83
- "results/Huggy2/Huggy/Huggy-1401988.pt"
84
  ]
85
  }
86
  },
 
72
  "auxillary_file_paths": [
73
  "results/Huggy2/Huggy/Huggy-1401988.pt"
74
  ]
75
+ },
76
+ {
77
+ "steps": 1599936,
78
+ "file_path": "results/Huggy2/Huggy/Huggy-1599936.onnx",
79
+ "reward": 3.612091050043211,
80
+ "creation_time": 1722513246.8450406,
81
+ "auxillary_file_paths": [
82
+ "results/Huggy2/Huggy/Huggy-1599936.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1799950,
87
+ "file_path": "results/Huggy2/Huggy/Huggy-1799950.onnx",
88
+ "reward": 4.151727098427462,
89
+ "creation_time": 1722513483.4980226,
90
+ "auxillary_file_paths": [
91
+ "results/Huggy2/Huggy/Huggy-1799950.pt"
92
+ ]
93
+ },
94
+ {
95
+ "steps": 1999919,
96
+ "file_path": "results/Huggy2/Huggy/Huggy-1999919.onnx",
97
+ "reward": 3.2546598660318473,
98
+ "creation_time": 1722513719.0368397,
99
+ "auxillary_file_paths": [
100
+ "results/Huggy2/Huggy/Huggy-1999919.pt"
101
+ ]
102
+ },
103
+ {
104
+ "steps": 2000015,
105
+ "file_path": "results/Huggy2/Huggy/Huggy-2000015.onnx",
106
+ "reward": 3.3931681752204894,
107
+ "creation_time": 1722513719.1548002,
108
+ "auxillary_file_paths": [
109
+ "results/Huggy2/Huggy/Huggy-2000015.pt"
110
+ ]
111
  }
112
  ],
113
  "final_checkpoint": {
114
+ "steps": 2000015,
115
  "file_path": "results/Huggy2/Huggy.onnx",
116
+ "reward": 3.3931681752204894,
117
+ "creation_time": 1722513719.1548002,
118
  "auxillary_file_paths": [
119
+ "results/Huggy2/Huggy/Huggy-2000015.pt"
120
  ]
121
  }
122
  },