Hugging Face's logo

chgenly
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
chgenly commited on
Commit
3d3e5f8
•
1 Parent(s): 613ee8b

First Push

Browse files
Files changed (29) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-249984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-249984.pt +3 -0
  4. SnowballTarget/SnowballTarget-299944.onnx +3 -0
  5. SnowballTarget/SnowballTarget-299944.pt +3 -0
  6. SnowballTarget/SnowballTarget-349968.onnx +3 -0
  7. SnowballTarget/SnowballTarget-349968.pt +3 -0
  8. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399968.pt +3 -0
  10. SnowballTarget/SnowballTarget-400224.onnx +3 -0
  11. SnowballTarget/SnowballTarget-400224.pt +3 -0
  12. SnowballTarget/SnowballTarget-449968.onnx +3 -0
  13. SnowballTarget/SnowballTarget-449968.pt +3 -0
  14. SnowballTarget/SnowballTarget-499992.onnx +3 -0
  15. SnowballTarget/SnowballTarget-499992.pt +3 -0
  16. SnowballTarget/SnowballTarget-549952.onnx +3 -0
  17. SnowballTarget/SnowballTarget-549952.pt +3 -0
  18. SnowballTarget/SnowballTarget-599952.onnx +3 -0
  19. SnowballTarget/SnowballTarget-599952.pt +3 -0
  20. SnowballTarget/SnowballTarget-600336.onnx +3 -0
  21. SnowballTarget/SnowballTarget-600336.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1694837211.e3d8d77e000d.5967.0 +3 -0
  24. SnowballTarget/events.out.tfevents.1694837636.e3d8d77e000d.7806.0 +3 -0
  25. config.json +1 -1
  26. configuration.yaml +2 -2
  27. run_logs/Player-0.log +13 -16
  28. run_logs/timers.json +136 -136
  29. run_logs/training_status.json +74 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48a15fc94b1f62ef7f1f755d59a0622d5d2d1248e86ce1c0aed39c2095eef11a
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14f7bd7623fce0fcb1376d8524d3012debd7c2aad64ffa37050e1a58937c27c
3
  size 646532
SnowballTarget/SnowballTarget-249984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed91fe4c4d9ac41eb0e6c724e64dae9dbe0ecacdef688341be1f85a8d5d95f7
3
+ size 646532
SnowballTarget/SnowballTarget-249984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7fc023837c14d494bfb1e355ba46c7673ff64cf7b7145f301703d57448c5ea
3
+ size 3843968
SnowballTarget/SnowballTarget-299944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f2f99ac8768ef26b99b1552790f2e26b3571d45e07cfc9c2840f4f0bbf17db
3
+ size 646532
SnowballTarget/SnowballTarget-299944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ed9122e5e2b18ca0776ea0a36cff4db639088b4fd2130e04640d6d8c2c44ec
3
+ size 3843968
SnowballTarget/SnowballTarget-349968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e7e69ef1dee03c391e0fb2e4a8b8cb831ce6b81bacf037cda8dae2721ec440
3
+ size 646532
SnowballTarget/SnowballTarget-349968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e6f95998261c38dda69995a04f6bed5fb9ab771643d84997da917adaff8056
3
+ size 3843968
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d2b11b127d7a0b9fc906f3af8936eb6174174c6c205ff79a12dce2b5019938
3
+ size 646532
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b500a666fd1fa01afe9366a11cb2d433a0bfaf0c41d71c3a4984c054c233ba
3
+ size 3843968
SnowballTarget/SnowballTarget-400224.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d2b11b127d7a0b9fc906f3af8936eb6174174c6c205ff79a12dce2b5019938
3
+ size 646532
SnowballTarget/SnowballTarget-400224.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7241790815bfffe47706c99b23d28f14ff78f9f4844f39e916ddb2c8dd4470f3
3
+ size 3843968
SnowballTarget/SnowballTarget-449968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3ce8c147376f821c16824f1a4b0b529383ff94e4511371d49f91310f4496f2
3
+ size 646532
SnowballTarget/SnowballTarget-449968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e51def2e9b453340acd75fa7a32b17f8e9795c4f3b37ffba1eced0b1bf92b0
3
+ size 3843968
SnowballTarget/SnowballTarget-499992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be4dab7ebb115fab7ed9c9d6db843d6b5ea8c12b9991d5690520ba87999871b1
3
+ size 646532
SnowballTarget/SnowballTarget-499992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1af51fd650b5f581fb2415bdc57712172dfd62b34f8dd25af5563ebfd19d00
3
+ size 3843968
SnowballTarget/SnowballTarget-549952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec0dd888b4521edeebafd43312784475c3ce84a9b8e894edd766ba9a16b6f87
3
+ size 646532
SnowballTarget/SnowballTarget-549952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9967973b580d7cb9c3aa207db0de59c747649c9fd3cc11e639ce25bf47104f6
3
+ size 3843968
SnowballTarget/SnowballTarget-599952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14f7bd7623fce0fcb1376d8524d3012debd7c2aad64ffa37050e1a58937c27c
3
+ size 646532
SnowballTarget/SnowballTarget-599952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fbe0f083e25326cf3474ac33664b0e818820452cd51aeb94c6392d199c4695
3
+ size 3843968
SnowballTarget/SnowballTarget-600336.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14f7bd7623fce0fcb1376d8524d3012debd7c2aad64ffa37050e1a58937c27c
3
+ size 646532
SnowballTarget/SnowballTarget-600336.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f8d7fb4737e6d78866cb1a53f5afcab5533a1935ba035c169d63f2321baf6a
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bcb1377ad59c9c2c99471009c4704f56f50a72c472f4039408cd3ab63112dda
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f8d7fb4737e6d78866cb1a53f5afcab5533a1935ba035c169d63f2321baf6a
3
  size 3843968
SnowballTarget/events.out.tfevents.1694837211.e3d8d77e000d.5967.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5419b6978ff07de9109bbe0e1c529ebcc21d1a9cfe5911f10ff328c93c1dd8
3
+ size 17522
SnowballTarget/events.out.tfevents.1694837636.e3d8d77e000d.7806.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660cc7f58463001a475e326218b526f91d24dbbe4c96d68dec4935c777a71cbd
3
+ size 17474
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, "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": "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": {"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": 600000, "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, "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": "SnowballTarget1", "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: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -67,7 +67,7 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
- resume: false
71
  force: false
72
  train_model: false
73
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 600000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
  force: false
72
  train_model: false
73
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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 0.082 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.689353 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 4 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -199,19 +196,19 @@ Memory Statistics:
199
  Peak Allocated Bytes 0 B
200
  Overflow Count 0
201
  [ALLOC_DEFAULT] Dual Thread Allocator
202
- Peak main deferred allocation count 33
203
  [ALLOC_BUCKET]
204
  Large Block size 4.0 MB
205
  Used Block count 1
206
  Peak Allocated bytes 1.0 MB
207
  [ALLOC_DEFAULT_MAIN]
208
- Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
209
  Requested Block Size 16.0 MB
210
  Peak Block count 1
211
  Peak Allocated memory 6.8 MB
212
  Peak Large allocation bytes 0 B
213
  [ALLOC_DEFAULT_THREAD]
214
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
215
  Requested Block Size 16.0 MB
216
  Peak Block count 1
217
  Peak Allocated memory 17.6 MB
@@ -243,13 +240,13 @@ Memory Statistics:
243
  Used Block count 1
244
  Peak Allocated bytes 1.0 MB
245
  [ALLOC_GFX_MAIN]
246
- Peak usage frame count: [32.0 KB-64.0 KB]: 4830 frames, [64.0 KB-128.0 KB]: 632 frames
247
  Requested Block Size 16.0 MB
248
  Peak Block count 1
249
- Peak Allocated memory 66.8 KB
250
  Peak Large allocation bytes 0 B
251
  [ALLOC_GFX_THREAD]
252
- Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
253
  Requested Block Size 16.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 39.6 KB
@@ -261,13 +258,13 @@ Memory Statistics:
261
  Used Block count 1
262
  Peak Allocated bytes 1.0 MB
263
  [ALLOC_CACHEOBJECTS_MAIN]
264
- Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
265
  Requested Block Size 4.0 MB
266
  Peak Block count 1
267
  Peak Allocated memory 0.6 MB
268
  Peak Large allocation bytes 0 B
269
  [ALLOC_CACHEOBJECTS_THREAD]
270
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
271
  Requested Block Size 4.0 MB
272
  Peak Block count 1
273
  Peak Allocated memory 2.2 MB
@@ -279,13 +276,13 @@ Memory Statistics:
279
  Used Block count 1
280
  Peak Allocated bytes 1.0 MB
281
  [ALLOC_TYPETREE_MAIN]
282
- Peak usage frame count: [0-1.0 KB]: 5462 frames
283
  Requested Block Size 2.0 MB
284
  Peak Block count 1
285
  Peak Allocated memory 1.0 KB
286
  Peak Large allocation bytes 0 B
287
  [ALLOC_TYPETREE_THREAD]
288
- Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
289
  Requested Block Size 2.0 MB
290
  Peak Block count 1
291
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_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/training-envs-executables/linux/SnowballTarget/SnowballTarget_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 0.083 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.667607 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 4 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
196
  Peak Allocated Bytes 0 B
197
  Overflow Count 0
198
  [ALLOC_DEFAULT] Dual Thread Allocator
199
+ Peak main deferred allocation count 32
200
  [ALLOC_BUCKET]
201
  Large Block size 4.0 MB
202
  Used Block count 1
203
  Peak Allocated bytes 1.0 MB
204
  [ALLOC_DEFAULT_MAIN]
205
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
206
  Requested Block Size 16.0 MB
207
  Peak Block count 1
208
  Peak Allocated memory 6.8 MB
209
  Peak Large allocation bytes 0 B
210
  [ALLOC_DEFAULT_THREAD]
211
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
212
  Requested Block Size 16.0 MB
213
  Peak Block count 1
214
  Peak Allocated memory 17.6 MB
 
240
  Used Block count 1
241
  Peak Allocated bytes 1.0 MB
242
  [ALLOC_GFX_MAIN]
243
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5296 frames, [64.0 KB-128.0 KB]: 165 frames
244
  Requested Block Size 16.0 MB
245
  Peak Block count 1
246
+ Peak Allocated memory 66.3 KB
247
  Peak Large allocation bytes 0 B
248
  [ALLOC_GFX_THREAD]
249
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
250
  Requested Block Size 16.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 39.6 KB
 
258
  Used Block count 1
259
  Peak Allocated bytes 1.0 MB
260
  [ALLOC_CACHEOBJECTS_MAIN]
261
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
262
  Requested Block Size 4.0 MB
263
  Peak Block count 1
264
  Peak Allocated memory 0.6 MB
265
  Peak Large allocation bytes 0 B
266
  [ALLOC_CACHEOBJECTS_THREAD]
267
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
268
  Requested Block Size 4.0 MB
269
  Peak Block count 1
270
  Peak Allocated memory 2.2 MB
 
276
  Used Block count 1
277
  Peak Allocated bytes 1.0 MB
278
  [ALLOC_TYPETREE_MAIN]
279
+ Peak usage frame count: [0-1.0 KB]: 5461 frames
280
  Requested Block Size 2.0 MB
281
  Peak Block count 1
282
  Peak Allocated memory 1.0 KB
283
  Peak Large allocation bytes 0 B
284
  [ALLOC_TYPETREE_THREAD]
285
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
286
  Requested Block Size 2.0 MB
287
  Peak Block count 1
288
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,39 +2,39 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.900482177734375,
6
- "min": 0.900482177734375,
7
- "max": 2.874271869659424,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8627.51953125,
12
- "min": 8627.51953125,
13
- "max": 29530.26953125,
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": 12.45028305053711,
30
- "min": 0.39966118335723877,
31
- "max": 12.45028305053711,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2427.80517578125,
36
- "min": 77.53427124023438,
37
- "max": 2511.990966796875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06266274304852784,
54
- "min": 0.0613157523922079,
55
- "max": 0.075099854782214,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.25065097219411137,
60
- "min": 0.25065097219411137,
61
- "max": 0.3535321011174578,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20227797015332707,
66
- "min": 0.11691818091796949,
67
- "max": 0.27010801902004317,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8091118806133083,
72
- "min": 0.46767272367187795,
73
- "max": 1.3505400951002158,
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": 24.318181818181817,
114
- "min": 3.227272727272727,
115
- "max": 24.927272727272726,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1070.0,
120
- "min": 142.0,
121
- "max": 1371.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.318181818181817,
126
- "min": 3.227272727272727,
127
- "max": 24.927272727272726,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1070.0,
132
- "min": 142.0,
133
- "max": 1371.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1694836238",
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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1694836595"
160
  },
161
- "total": 357.35891246500006,
162
  "count": 1,
163
- "self": 0.3246239760000549,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03960337400002345,
167
  "count": 1,
168
- "self": 0.03960337400002345
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 356.994685115,
172
  "count": 1,
173
- "self": 0.4516293720033673,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.13083302199999,
177
  "count": 1,
178
- "self": 4.13083302199999
179
  },
180
  "TrainerController.advance": {
181
- "total": 352.2792616129966,
182
- "count": 18205,
183
- "self": 0.22099274499680632,
184
  "children": {
185
  "env_step": {
186
- "total": 352.0582688679998,
187
- "count": 18205,
188
- "self": 259.7687726970035,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 92.0774001969964,
192
- "count": 18205,
193
- "self": 1.3077114339971558,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 90.76968876299924,
197
- "count": 18205,
198
- "self": 90.76968876299924
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21209597399990798,
204
- "count": 18205,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 356.29666728699567,
209
- "count": 18205,
210
  "is_parallel": true,
211
- "self": 177.8726022739948,
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": 0.002053332999992108,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0005422280001425861,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015111049998495218,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015111049998495218
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.02795646000004126,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006048570000416476,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00046127000001661145,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00046127000001661145
244
  },
245
  "communicator.exchange": {
246
- "total": 0.023927329999992253,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.023927329999992253
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0029630029999907492,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00037208700007340667,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0025909159999173426,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0025909159999173426
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 178.42406501300087,
271
- "count": 18204,
272
  "is_parallel": true,
273
- "self": 7.28728134199946,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 3.7329295490056325,
277
- "count": 18204,
278
  "is_parallel": true,
279
- "self": 3.7329295490056325
280
  },
281
  "communicator.exchange": {
282
- "total": 144.3535413459951,
283
- "count": 18204,
284
  "is_parallel": true,
285
- "self": 144.3535413459951
286
  },
287
  "steps_from_proto": {
288
- "total": 23.05031277600068,
289
- "count": 18204,
290
  "is_parallel": true,
291
- "self": 4.160458119002442,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 18.88985465699824,
295
- "count": 182040,
296
  "is_parallel": true,
297
- "self": 18.88985465699824
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.000153051999973286,
313
  "count": 1,
314
- "self": 0.000153051999973286,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 351.29184617200843,
324
- "count": 208190,
325
  "is_parallel": true,
326
- "self": 3.496784034001678,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 192.01539012300725,
330
- "count": 208190,
331
  "is_parallel": true,
332
- "self": 191.21967033400733,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.7957197889999179,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.7957197889999179
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 155.7796720149995,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 44.308655128998566,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 111.47101688600094,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 111.47101688600094
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.13280805600004442,
364
  "count": 1,
365
- "self": 0.000827069000024494,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13198098700001992,
369
  "count": 1,
370
- "self": 0.13198098700001992
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6372256278991699,
6
+ "min": 0.6304492354393005,
7
+ "max": 0.7413288354873657,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6448.72314453125,
12
+ "min": 6123.5537109375,
13
+ "max": 7600.10302734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 599952.0,
18
+ "min": 409984.0,
19
+ "max": 599952.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 599952.0,
24
+ "min": 409984.0,
25
+ "max": 599952.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.573698997497559,
30
+ "min": 13.207062721252441,
31
+ "max": 13.67253303527832,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2646.871337890625,
36
+ "min": 2562.0791015625,
37
+ "max": 2789.19677734375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06944811620101687,
54
+ "min": 0.06160803573610096,
55
+ "max": 0.07471052457951695,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2777924648040675,
60
+ "min": 0.26201602920841915,
61
+ "max": 0.37355262289758473,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.1575547485959296,
66
+ "min": 0.1575547485959296,
67
+ "max": 0.20449341912114738,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.6302189943837184,
72
+ "min": 0.6302189943837184,
73
+ "max": 0.9703168766755683,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 2.582099139333337e-06,
78
+ "min": 2.582099139333337e-06,
79
+ "max": 9.718206760599997e-05,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.0328396557333347e-05,
84
+ "min": 1.0328396557333347e-05,
85
+ "max": 0.00046116034627999996,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10086066666666667,
90
+ "min": 0.10086066666666667,
91
+ "max": 0.13239400000000004,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.40344266666666667,
96
+ "min": 0.40344266666666667,
97
+ "max": 0.6537200000000001,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 5.294726666666673e-05,
102
+ "min": 5.294726666666673e-05,
103
+ "max": 0.0016264606000000003,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0002117890666666669,
108
+ "min": 0.0002117890666666669,
109
+ "max": 0.007720628000000001,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.795454545454547,
114
+ "min": 25.59090909090909,
115
+ "max": 27.036363636363635,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1179.0,
120
+ "min": 1126.0,
121
+ "max": 1487.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.795454545454547,
126
+ "min": 25.59090909090909,
127
+ "max": 27.036363636363635,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1179.0,
132
+ "min": 1126.0,
133
+ "max": 1487.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1694837635",
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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --resume --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1694838002"
160
  },
161
+ "total": 367.19065737000005,
162
  "count": 1,
163
+ "self": 0.273493672000086,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0454269409999597,
167
  "count": 1,
168
+ "self": 0.0454269409999597
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 366.871736757,
172
  "count": 1,
173
+ "self": 0.5238358360088569,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 4.027539482000066,
177
  "count": 1,
178
+ "self": 4.027539482000066
179
  },
180
  "TrainerController.advance": {
181
+ "total": 362.1868134979911,
182
+ "count": 18202,
183
+ "self": 0.22542344800422143,
184
  "children": {
185
  "env_step": {
186
+ "total": 361.9613900499869,
187
+ "count": 18202,
188
+ "self": 266.93687646594435,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 94.78736859001924,
192
+ "count": 18202,
193
+ "self": 1.3577274790309275,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 93.42964111098831,
197
+ "count": 18202,
198
+ "self": 93.42964111098831
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.23714499402331057,
204
+ "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 366.10896869898716,
209
+ "count": 18202,
210
  "is_parallel": true,
211
+ "self": 183.55066692399282,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.001986266999892905,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006178289997933462,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013684380000995588,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013684380000995588
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.027899336000018593,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00042182799984402664,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0002940250001302047,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0002940250001302047
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.025274244000002,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.025274244000002
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.001909239000042362,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0009877020002022618,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0009215369998401002,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0009215369998401002
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 182.55830177499433,
271
+ "count": 18201,
272
  "is_parallel": true,
273
+ "self": 7.33239924293639,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.7956068410185253,
277
+ "count": 18201,
278
  "is_parallel": true,
279
+ "self": 3.7956068410185253
280
  },
281
  "communicator.exchange": {
282
+ "total": 147.8650812430094,
283
+ "count": 18201,
284
  "is_parallel": true,
285
+ "self": 147.8650812430094
286
  },
287
  "steps_from_proto": {
288
+ "total": 23.56521444803002,
289
+ "count": 18201,
290
  "is_parallel": true,
291
+ "self": 4.305381379084338,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 19.25983306894568,
295
+ "count": 182010,
296
  "is_parallel": true,
297
+ "self": 19.25983306894568
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.0003036520001842291,
313
  "count": 1,
314
+ "self": 0.0003036520001842291,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 361.23940356398793,
324
+ "count": 211361,
325
  "is_parallel": true,
326
+ "self": 3.6314317079313696,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 196.8941352970562,
330
+ "count": 211361,
331
  "is_parallel": true,
332
+ "self": 196.12222567305616,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.7719096240000454,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.7719096240000454
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 160.71383655900036,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 46.63256134998596,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 114.0812752090144,
350
+ "count": 4587,
351
  "is_parallel": true,
352
+ "self": 114.0812752090144
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.13324428899977647,
364
  "count": 1,
365
+ "self": 0.001086108999516,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.13215818000026047,
369
  "count": 1,
370
+ "self": 0.13215818000026047
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 11.545454545454545,
8
- "creation_time": 1694836330.8303118,
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": 20.181818181818183,
17
- "creation_time": 1694836419.252403,
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": 24.636363636363637,
26
- "creation_time": 1694836507.4912844,
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": 24.363636363636363,
35
- "creation_time": 1694836595.4742444,
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": 24.363636363636363,
44
- "creation_time": 1694836595.6284695,
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": 24.363636363636363,
54
- "creation_time": 1694836595.6284695,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 249984,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
7
+ "reward": 26.727272727272727,
8
+ "creation_time": 1694837307.2905755,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 299944,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
16
+ "reward": 26.0,
17
+ "creation_time": 1694837398.7012289,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 349968,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
25
+ "reward": 27.0,
26
+ "creation_time": 1694837492.051726,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 399968,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
34
+ "reward": 26.90909090909091,
35
+ "creation_time": 1694837581.9936156,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 400224,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.onnx",
43
+ "reward": 26.90909090909091,
44
+ "creation_time": 1694837582.1689003,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 449968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449968.onnx",
52
+ "reward": 26.09090909090909,
53
+ "creation_time": 1694837730.0036335,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 499992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499992.onnx",
61
+ "reward": 25.727272727272727,
62
+ "creation_time": 1694837821.5863163,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 549952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549952.onnx",
70
+ "reward": 27.0,
71
+ "creation_time": 1694837912.4318275,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-549952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 599952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.onnx",
79
+ "reward": 27.545454545454547,
80
+ "creation_time": 1694838002.385148,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 600336,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-600336.onnx",
88
+ "reward": 27.545454545454547,
89
+ "creation_time": 1694838002.5615811,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-600336.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 600336,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 27.545454545454547,
99
+ "creation_time": 1694838002.5615811,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-600336.pt"
102
  ]
103
  }
104
  },