Hugging Face's logo

LemonIsGoose
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
LemonIsGoose commited on
Commit
50697d7
·
verified ·
1 Parent(s): 540cdb4

First Push

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000120.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000120.pt +3 -0
  4. SnowballTarget/SnowballTarget-599976.onnx +3 -0
  5. SnowballTarget/SnowballTarget-599976.pt +3 -0
  6. SnowballTarget/SnowballTarget-649936.onnx +3 -0
  7. SnowballTarget/SnowballTarget-649936.pt +3 -0
  8. SnowballTarget/SnowballTarget-699960.onnx +3 -0
  9. SnowballTarget/SnowballTarget-699960.pt +3 -0
  10. SnowballTarget/SnowballTarget-749960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-749960.pt +3 -0
  12. SnowballTarget/SnowballTarget-799984.onnx +3 -0
  13. SnowballTarget/SnowballTarget-799984.pt +3 -0
  14. SnowballTarget/SnowballTarget-849944.onnx +3 -0
  15. SnowballTarget/SnowballTarget-849944.pt +3 -0
  16. SnowballTarget/SnowballTarget-899968.onnx +3 -0
  17. SnowballTarget/SnowballTarget-899968.pt +3 -0
  18. SnowballTarget/SnowballTarget-949968.onnx +3 -0
  19. SnowballTarget/SnowballTarget-949968.pt +3 -0
  20. SnowballTarget/SnowballTarget-999992.onnx +3 -0
  21. SnowballTarget/SnowballTarget-999992.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1761814723.a29d83604da8.9845.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +2 -2
  26. run_logs/Player-0.log +16 -19
  27. run_logs/timers.json +162 -162
  28. 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:e40a595507a82433b8908f414016bc9a3549f98e0dabe42480eb3d2b186774b0
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b491efdb1b4c69c774a66248e6540bdee8267d2d4ffa94fa02ea0e10a4146344
3
  size 650646
SnowballTarget/SnowballTarget-1000120.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b491efdb1b4c69c774a66248e6540bdee8267d2d4ffa94fa02ea0e10a4146344
3
+ size 650646
SnowballTarget/SnowballTarget-1000120.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6fd85f883de6ff4fb7b11825f70aeab17d5ab543f02e39244a5d4e3d845ee60
3
+ size 3850705
SnowballTarget/SnowballTarget-599976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73600547fd510d9e6b09816d66af6c4d11cf42a1ccb279d9d2c44c91fa218e1e
3
+ size 650646
SnowballTarget/SnowballTarget-599976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bdc39b35ca705f13262d955ff969c72c7e38fd9f25638123ebcdf810fd77f9a
3
+ size 3850564
SnowballTarget/SnowballTarget-649936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb6129d27662c9f9b34e1eba5706843b3459948cd609990a24808ea2d3ec3bf
3
+ size 650646
SnowballTarget/SnowballTarget-649936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc7ba2c5ee76711f3688103b7edc89223d113123b2052e4b33261cd4b972bcb3
3
+ size 3850564
SnowballTarget/SnowballTarget-699960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84285bcdbe9d661f6a7fbd7a65039821ec42a095ac8230ac8ada19b1e030db96
3
+ size 650646
SnowballTarget/SnowballTarget-699960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14906af986c866d348d12b43717cc2b6e255b71407cd7507b57eebfa81c3eedb
3
+ size 3850564
SnowballTarget/SnowballTarget-749960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8deaa8fc69f035a49f9633f0df9df5cb310173f16c68b1b53ade0f00632e8ec5
3
+ size 650646
SnowballTarget/SnowballTarget-749960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f264c7f8a13ea1bb2765b67c467dcbe1b26f897ad77e313f969d9427c993b4
3
+ size 3850564
SnowballTarget/SnowballTarget-799984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf38e786a3a2a629a6e33ca197f142761ac20fa15ab82da452abc90248b8e62a
3
+ size 650646
SnowballTarget/SnowballTarget-799984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da00e24e45df45d16d2886d75c1440397a95b8352ad1fa5f83214eee2c23c2d
3
+ size 3850564
SnowballTarget/SnowballTarget-849944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f2ad8d67a442a87d9f6e60a3948467e9198d39dec7fcad10a37f8358636c7c
3
+ size 650646
SnowballTarget/SnowballTarget-849944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d8a2b3cd6c8fbac4ae5a22ed1cc0ea3016bcff43182e9b95766e16145f46b8
3
+ size 3850564
SnowballTarget/SnowballTarget-899968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86eab50a8737f534f75331a91e6324de7a3c65517ee72f633b08d1b0653e6df1
3
+ size 650646
SnowballTarget/SnowballTarget-899968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce72e7170ec2e4692dc7d8b6eb57ba40e4ab50697e542eba1b8709e433c1bffc
3
+ size 3850564
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b462460ff0f74bc012da2f653f737799e4ced3555648cd45e7b23e59c5d205
3
+ size 650646
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2385970c85bb0878925c7c8127dc2861fbc9d99eba7a0ec9640651a0105ab0f
3
+ size 3850564
SnowballTarget/SnowballTarget-999992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b491efdb1b4c69c774a66248e6540bdee8267d2d4ffa94fa02ea0e10a4146344
3
+ size 650646
SnowballTarget/SnowballTarget-999992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6ea39622f95c84f61772938bc4bda3bf0b70a73ebf1b870f133dc8270d1f23
3
+ size 3850564
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20609b0c2916dd0f319c2f30c841946ade255f03d916ea3e3ff4f8e9ffd107ed
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf540e0d14e57ada1c95f47674f3b7a6cd30c2972541c6632570c1d1c9799e3
3
  size 3849717
SnowballTarget/events.out.tfevents.1761814723.a29d83604da8.9845.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb3594f334ecae64cb9e55241c6bf1378d697b6f4ecb82fcb51bc22dfcc9b10
3
+ size 67082
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": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"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": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": 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: false
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
 
69
  run_id: SnowballTarget1
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/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 0.132 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: 0.855667 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 1 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 42
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
179
  Requested Block Size 16.0 MB
180
- Peak Block count 1
181
- Peak Allocated memory 7.2 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.3 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 3758 frames, [64.0 KB-128.0 KB]: 1700 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5458 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  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 0.084 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: 0.665331 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 1 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]: 21455 frames, [16.0 KB-32.0 KB]: 363 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
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 40
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 10258 frames, [8.0 MB-16.0 MB]: 11561 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 13.3 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 21819 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 16969 frames, [64.0 KB-128.0 KB]: 4850 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 68.5 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 21819 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 21819 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 21818 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 21819 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 21819 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.7596582770347595,
6
- "min": 0.7229508757591248,
7
- "max": 2.8453519344329834,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7219.79248046875,
12
- "min": 6934.64013671875,
13
- "max": 29045.353515625,
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": 11.9436674118042,
30
- "min": 0.27258893847465515,
31
- "max": 11.9436674118042,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2329.01513671875,
36
- "min": 52.88225173950195,
37
- "max": 2414.22412109375,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.0707581027818378,
42
- "min": 0.05741717984532371,
43
- "max": 0.07480861071643291,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2830324111273512,
48
- "min": 0.22966871938129485,
49
- "max": 0.37404305358216455,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.1724290989850666,
54
- "min": 0.12667423289260077,
55
- "max": 0.26688409576229016,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.6897163959402663,
60
- "min": 0.5066969315704031,
61
- "max": 1.3344204788114509,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 23.363636363636363,
114
- "min": 3.659090909090909,
115
- "max": 23.527272727272727,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1028.0,
120
- "min": 161.0,
121
- "max": 1294.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.363636363636363,
126
- "min": 3.659090909090909,
127
- "max": 23.527272727272727,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1028.0,
132
- "min": 161.0,
133
- "max": 1294.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1761813308",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1761813759"
160
  },
161
- "total": 451.2245761370001,
162
  "count": 1,
163
- "self": 0.4335086560000718,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04922662199999195,
167
  "count": 1,
168
- "self": 0.04922662199999195
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 450.74184085900004,
172
  "count": 1,
173
- "self": 0.35860116398771424,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.011620934000007,
177
  "count": 1,
178
- "self": 3.011620934000007
179
  },
180
  "TrainerController.advance": {
181
- "total": 447.29203485101243,
182
- "count": 18192,
183
- "self": 0.3893260390133264,
184
  "children": {
185
  "env_step": {
186
- "total": 326.4811374760135,
187
- "count": 18192,
188
- "self": 255.98841755600802,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 70.27576141000475,
192
- "count": 18192,
193
- "self": 1.2781766079914405,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 68.99758480201331,
197
- "count": 18192,
198
- "self": 68.99758480201331
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.21695851000072253,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 449.0452567069847,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 223.9827805209925,
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": 0.004972980000047755,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0035360020001462544,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014369779999015009,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014369779999015009
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03618927499996971,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006290090000220516,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00038437999990037497,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00038437999990037497
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03322822899997391,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03322822899997391
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019476570000733773,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00037424000026931026,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001573416999804067,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001573416999804067
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 225.06247618599218,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.592659689968514,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.6702545650057345,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.6702545650057345
280
  },
281
  "communicator.exchange": {
282
- "total": 171.05400111200322,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 171.05400111200322
286
  },
287
  "steps_from_proto": {
288
- "total": 37.74556081901471,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 6.754282632982381,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 30.991278186032332,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 30.991278186032332
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 120.42157133598562,
311
- "count": 18192,
312
- "self": 0.44964293596854077,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.945256381016065,
316
- "count": 18192,
317
- "self": 26.34527615901618,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.5999802219998855,
321
- "count": 4,
322
- "self": 0.5999802219998855
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 93.02667201900101,
328
- "count": 90,
329
- "self": 38.06316997899262,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 54.96350204000839,
333
- "count": 4587,
334
- "self": 54.96350204000839
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.929999578162096e-07,
344
  "count": 1,
345
- "self": 9.929999578162096e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07958291699992515,
349
  "count": 1,
350
- "self": 0.0007084510000368027,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07887446599988834,
354
  "count": 1,
355
- "self": 0.07887446599988834
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.374580442905426,
6
+ "min": 0.3643650412559509,
7
+ "max": 0.7337501645088196,
8
+ "count": 80
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 3560.012451171875,
12
+ "min": 3529.580078125,
13
+ "max": 7490.12158203125,
14
+ "count": 80
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999992.0,
18
+ "min": 209936.0,
19
+ "max": 999992.0,
20
+ "count": 80
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999992.0,
24
+ "min": 209936.0,
25
+ "max": 999992.0,
26
+ "count": 80
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.95432186126709,
30
+ "min": 11.86744213104248,
31
+ "max": 13.021476745605469,
32
+ "count": 80
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2526.0927734375,
36
+ "min": 2292.9599609375,
37
+ "max": 2656.4658203125,
38
+ "count": 80
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.0724045507462613,
42
+ "min": 0.05778585477131784,
43
+ "max": 0.07941376969193145,
44
+ "count": 80
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2896182029850452,
48
+ "min": 0.23114341908527136,
49
+ "max": 0.3843103292450656,
50
+ "count": 80
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.14879775901927667,
54
+ "min": 0.13513713610522887,
55
+ "max": 0.20789627343708394,
56
+ "count": 80
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.5951910360771067,
60
+ "min": 0.5439493631323179,
61
+ "max": 1.0064598821541844,
62
+ "count": 80
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 1.402899532400004e-06,
66
+ "min": 1.402899532400004e-06,
67
+ "max": 0.0002383428205524,
68
+ "count": 80
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 5.611598129600016e-06,
72
+ "min": 5.611598129600016e-06,
73
+ "max": 0.001176864107712,
74
+ "count": 80
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.1004676,
78
+ "min": 0.1004676,
79
+ "max": 0.1794476,
80
+ "count": 80
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.4018704,
84
+ "min": 0.4018704,
85
+ "max": 0.892288,
86
+ "count": 80
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 3.3333240000000065e-05,
90
+ "min": 3.3333240000000065e-05,
91
+ "max": 0.00397443524,
92
+ "count": 80
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00013333296000000026,
96
+ "min": 0.00013333296000000026,
97
+ "max": 0.0196251712,
98
+ "count": 80
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 80
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 80
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.386363636363637,
114
+ "min": 23.0,
115
+ "max": 25.522727272727273,
116
+ "count": 80
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1117.0,
120
+ "min": 1020.0,
121
+ "max": 1400.0,
122
+ "count": 80
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.386363636363637,
126
+ "min": 23.0,
127
+ "max": 25.522727272727273,
128
+ "count": 80
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1117.0,
132
+ "min": 1020.0,
133
+ "max": 1400.0,
134
+ "count": 80
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 80
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 80
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1761814723",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
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 --resume",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1761816522"
160
  },
161
+ "total": 1799.3915474189998,
162
  "count": 1,
163
+ "self": 0.7804227439996794,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0249263420000716,
167
  "count": 1,
168
+ "self": 0.0249263420000716
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1798.586198333,
172
  "count": 1,
173
+ "self": 1.506672090992197,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.917800995000107,
177
  "count": 1,
178
+ "self": 1.917800995000107
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1795.0394984730078,
182
+ "count": 72728,
183
+ "self": 1.4946366171966474,
184
  "children": {
185
  "env_step": {
186
+ "total": 1311.3305661559857,
187
+ "count": 72728,
188
+ "self": 1027.8489127318721,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 282.5614591920603,
192
+ "count": 72728,
193
+ "self": 5.177399152053113,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 277.38406004000717,
197
+ "count": 72728,
198
+ "self": 277.38406004000717
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.9201942320532908,
204
+ "count": 72728,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1792.333856837914,
209
+ "count": 72728,
210
  "is_parallel": true,
211
+ "self": 887.5131611378256,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002112542000304529,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006674189999102964,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0014451230003942328,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0014451230003942328
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.036311199000010674,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005774600008408015,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00047467899958064663,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00047467899958064663
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03347014599967224,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03347014599967224
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017889139999169856,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003405359998396307,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001448378000077355,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001448378000077355
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 904.8206957000884,
271
+ "count": 72727,
272
  "is_parallel": true,
273
+ "self": 41.832635985086654,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 23.16762553002809,
277
+ "count": 72727,
278
  "is_parallel": true,
279
+ "self": 23.16762553002809
280
  },
281
  "communicator.exchange": {
282
+ "total": 688.5721447390097,
283
+ "count": 72727,
284
  "is_parallel": true,
285
+ "self": 688.5721447390097
286
  },
287
  "steps_from_proto": {
288
+ "total": 151.24828944596402,
289
+ "count": 72727,
290
  "is_parallel": true,
291
+ "self": 27.119742071854034,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 124.12854737410998,
295
+ "count": 727270,
296
  "is_parallel": true,
297
+ "self": 124.12854737410998
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 482.21429569982547,
311
+ "count": 72728,
312
+ "self": 1.873519834840863,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 105.22609955198868,
316
+ "count": 72728,
317
+ "self": 103.67849293198788,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 1.5476066200008063,
321
+ "count": 16,
322
+ "self": 1.5476066200008063
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 375.1146763129959,
328
+ "count": 363,
329
+ "self": 152.87356081701228,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 222.24111549598365,
333
+ "count": 18510,
334
+ "self": 222.24111549598365
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.1219999578315765e-06,
344
  "count": 1,
345
+ "self": 1.1219999578315765e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.12222565199999735,
349
  "count": 1,
350
+ "self": 0.001639331000205857,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.1205863209997915,
354
  "count": 1,
355
+ "self": 0.1205863209997915
356
  }
357
  }
358
  }
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": 14.181818181818182,
8
- "creation_time": 1761813423.3865602,
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": 20.727272727272727,
17
- "creation_time": 1761813534.3176112,
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": 23.0,
26
- "creation_time": 1761813645.27189,
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": 22.363636363636363,
35
- "creation_time": 1761813759.3397703,
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": 22.363636363636363,
44
- "creation_time": 1761813759.431805,
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": 22.363636363636363,
54
- "creation_time": 1761813759.431805,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 599976,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
7
+ "reward": 25.272727272727273,
8
+ "creation_time": 1761815631.8727372,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 649936,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
16
+ "reward": 24.454545454545453,
17
+ "creation_time": 1761815743.6424809,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 699960,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.onnx",
25
+ "reward": 25.181818181818183,
26
+ "creation_time": 1761815855.7107902,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-699960.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 749960,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
34
+ "reward": 25.727272727272727,
35
+ "creation_time": 1761815967.5466902,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 799984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
43
+ "reward": 24.727272727272727,
44
+ "creation_time": 1761816081.0399015,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 849944,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
52
+ "reward": 25.272727272727273,
53
+ "creation_time": 1761816190.8232446,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 899968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.onnx",
61
+ "reward": 25.09090909090909,
62
+ "creation_time": 1761816302.370902,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-899968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 949968,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
70
+ "reward": 25.636363636363637,
71
+ "creation_time": 1761816411.704237,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 999992,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
79
+ "reward": 24.818181818181817,
80
+ "creation_time": 1761816521.4571352,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1000120,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
88
+ "reward": 24.818181818181817,
89
+ "creation_time": 1761816521.7206788,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000120,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 24.818181818181817,
99
+ "creation_time": 1761816521.7206788,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
102
  ]
103
  }
104
  },