Hugging Face's logo

kupru
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
kupru commited on
Commit
0ab642b
·
1 Parent(s): 4d2cebb

first attempt

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149800.onnx +3 -0
  3. SnowballTarget/SnowballTarget-149800.pt +3 -0
  4. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-149984.pt +1 -1
  6. SnowballTarget/SnowballTarget-180400.onnx +3 -0
  7. SnowballTarget/SnowballTarget-180400.pt +3 -0
  8. SnowballTarget/SnowballTarget-199800.onnx +3 -0
  9. SnowballTarget/SnowballTarget-199800.pt +3 -0
  10. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  11. SnowballTarget/SnowballTarget-199984.pt +1 -1
  12. SnowballTarget/SnowballTarget-200200.onnx +3 -0
  13. SnowballTarget/SnowballTarget-200200.pt +3 -0
  14. SnowballTarget/SnowballTarget-49800.onnx +3 -0
  15. SnowballTarget/SnowballTarget-49800.pt +3 -0
  16. SnowballTarget/SnowballTarget-49952.onnx +3 -0
  17. SnowballTarget/SnowballTarget-49952.pt +3 -0
  18. SnowballTarget/SnowballTarget-99800.onnx +3 -0
  19. SnowballTarget/SnowballTarget-99800.pt +3 -0
  20. SnowballTarget/SnowballTarget-99896.onnx +3 -0
  21. SnowballTarget/SnowballTarget-99896.pt +3 -0
  22. SnowballTarget/checkpoint.pt +1 -1
  23. SnowballTarget/events.out.tfevents.1695401511.b12cb4178495.38096.0 +3 -0
  24. config.json +1 -1
  25. configuration.yaml +4 -4
  26. run_logs/Player-0.log +14 -17
  27. run_logs/timers.json +156 -156
  28. run_logs/training_status.json +29 -29
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ee0483f6fde00d85b83faaa0dcd5aa00b76af366845673b4a1693c62557d85
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
3
  size 646532
SnowballTarget/SnowballTarget-149800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ae8230c8ef481cbe8dd45a3acca3d363e5e273426515ac57c022cf6703776e
3
+ size 646532
SnowballTarget/SnowballTarget-149800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead86d8fbe68fbbeca2bd21975c1e6aed77011115c076185269ee41ea739e738
3
+ size 3843968
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe3eb0bebe3a96aa791b2e57cb0b627b2401e4ddf9b94a1a8e34a81392cd1988
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a855931a9c292fa992f49e8fa7c86d184444a5c260faddb90ea7963bd6dc9be
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf4ba6b2210a37e004ddf49c0b7f9c9ef752eef6fc4d96b81cf2d46630441a0d
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22346cf76fac75fd80eea0437877147b6fb0d3c92fa7debccb67d739d0efa3b
3
  size 3843968
SnowballTarget/SnowballTarget-180400.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0096ff72b20dbe868a5364435f23065812d1d51b0bc4edd97fed5af26189b6fb
3
+ size 646532
SnowballTarget/SnowballTarget-180400.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2150ca8dbb3f81ceece1036afad10bc10af2479c1054e77d44af1d357772f0
3
+ size 3843968
SnowballTarget/SnowballTarget-199800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
3
+ size 646532
SnowballTarget/SnowballTarget-199800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ed3e272cddcc5e08140c6c0327e0379a77eaf6178a9a9e74db3ee26db6f0db
3
+ size 3843968
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ee0483f6fde00d85b83faaa0dcd5aa00b76af366845673b4a1693c62557d85
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e921599490596056f50cdc872e7c2eec825d7bd7547aba5b1484a51b248d56c7
3
  size 646532
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a95d06a972598a8a4187a0b1ab1b38177613ae8d6761ff295b08f1c8a14e8889
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0090e049472e213380a1fb6f00a76e5c6c9f4dc50bbd1318ec7a7c092ebe66b
3
  size 3843968
SnowballTarget/SnowballTarget-200200.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0114b7504287238e035d0e3d0e97728c844b4281fccd4d8390bf7b38a66a26e5
3
+ size 646532
SnowballTarget/SnowballTarget-200200.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532f7c097a0ed8694e9c4822be6d505d9ed870087f07d87313c4f1f37758df9a
3
+ size 3843968
SnowballTarget/SnowballTarget-49800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fefb87f80b8d5774f4faf6b974cce35c0eb16c5fd4c7d979c722a5171e92b58
3
+ size 646532
SnowballTarget/SnowballTarget-49800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1c8644454fa345bbb8377d9ccfe8bca37b1227920f0836f555a9cb0e95c6a7
3
+ size 3843968
SnowballTarget/SnowballTarget-49952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8bc0f9be79217433f74b39b947d30f16f299feda66a87ad66867cfaff028ce
3
+ size 646532
SnowballTarget/SnowballTarget-49952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d63c4dce7ffa1002aba3821c2b85e330ff6b1a8de372e97492f077d754d79f
3
+ size 3843968
SnowballTarget/SnowballTarget-99800.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78886b05b8928a18d70ac0d7ad93b4001f73b86166a093efb7596b4396dfc2b
3
+ size 646532
SnowballTarget/SnowballTarget-99800.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5623c533decebf6d7f9b5a66fc14c88637fea8a63a0bd58d0997c68abfa7bf
3
+ size 3843968
SnowballTarget/SnowballTarget-99896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9b1a3fac0ac7f13c22e81d402fda4be39d4eeae07e0db1c6f571040c8abed1
3
+ size 646532
SnowballTarget/SnowballTarget-99896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbb870e3f0cff3cd28884ab3554b8ef52c031b5141b5ba87c28c024bc91ac18
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b61232ddee2b11d13f90f75188677fda5f3254e949d5cb74fe5730a2e48d7b5
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532f7c097a0ed8694e9c4822be6d505d9ed870087f07d87313c4f1f37758df9a
3
  size 3843968
SnowballTarget/events.out.tfevents.1695401511.b12cb4178495.38096.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802fb152758dc1cd5415c1b3dd6002c25cdafbc0992e2130657d328e64c0d362
3
+ size 28719
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": 0.005, "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": 0.95, "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": 256, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
@@ -25,7 +25,7 @@ behaviors:
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.99
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
@@ -39,7 +39,7 @@ behaviors:
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
  max_steps: 200000
42
- time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
@@ -68,7 +68,7 @@ checkpoint_settings:
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
- force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.005
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.95
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
 
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
  max_steps: 200000
42
+ time_horizon: 256
43
  summary_freq: 10000
44
  threaded: true
45
  self_play: null
 
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
+ force: true
72
  train_model: false
73
  inference: false
74
  results_dir: results
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 0.079 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: 0.650181 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]: 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
@@ -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 41
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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 7.1 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 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]: 4731 frames, [64.0 KB-128.0 KB]: 731 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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 0.144 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: 0.852645 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]: 5373 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
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 46
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]: 5465 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.9 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5465 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.5 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]: 5022 frames, [64.0 KB-128.0 KB]: 443 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5465 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]: 5465 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]: 5464 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]: 5465 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]: 5465 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
@@ -2,135 +2,135 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9905679821968079,
6
- "min": 0.9905679821968079,
7
- "max": 2.870112419128418,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9479.7353515625,
12
- "min": 9479.7353515625,
13
- "max": 29392.8203125,
 
 
 
 
 
 
 
 
 
 
 
 
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": 12.542269706726074,
30
- "min": 0.436093270778656,
31
- "max": 12.641898155212402,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2445.74267578125,
36
- "min": 84.60209655761719,
37
- "max": 2578.947265625,
38
  "count": 20
39
  },
40
- "SnowballTarget.Environment.EpisodeLength.mean": {
41
- "value": 199.0,
42
- "min": 199.0,
43
- "max": 199.0,
44
  "count": 20
45
  },
46
- "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
- "min": 8756.0,
49
- "max": 10945.0,
 
 
 
 
 
 
 
 
 
 
 
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06483898489372508,
54
- "min": 0.06352636912976653,
55
- "max": 0.07632039742772986,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.25935593957490033,
60
- "min": 0.2541054765190661,
61
- "max": 0.37813210600242936,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21808049170409932,
66
- "min": 0.1486261908556152,
67
- "max": 0.2853587735517352,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8723219668163973,
72
- "min": 0.5945047634224608,
73
- "max": 1.426793867758676,
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": 24.25,
114
- "min": 3.659090909090909,
115
- "max": 25.136363636363637,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1067.0,
120
- "min": 161.0,
121
- "max": 1371.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.25,
126
- "min": 3.659090909090909,
127
- "max": 25.136363636363637,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1067.0,
132
- "min": 161.0,
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": "1695394432",
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": "1695394901"
160
  },
161
- "total": 468.565025098,
162
  "count": 1,
163
- "self": 0.4315352239996173,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04176162900012059,
167
  "count": 1,
168
- "self": 0.04176162900012059
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 468.09172824500024,
172
  "count": 1,
173
- "self": 0.514204477987505,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 5.107928096000023,
177
  "count": 1,
178
- "self": 5.107928096000023
179
  },
180
  "TrainerController.advance": {
181
- "total": 462.3062296520127,
182
- "count": 18204,
183
- "self": 0.259350869028367,
184
  "children": {
185
  "env_step": {
186
- "total": 462.0468787829843,
187
- "count": 18204,
188
- "self": 335.5412605870131,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 126.23264098198888,
192
- "count": 18204,
193
- "self": 1.7489456039616016,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 124.48369537802728,
197
- "count": 18204,
198
- "self": 124.48369537802728
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2729772139823581,
204
- "count": 18204,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 466.533233262963,
209
- "count": 18204,
210
  "is_parallel": true,
211
- "self": 221.27764433995458,
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": 0.005599847999974372,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003952773999799319,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0016470740001750528,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0016470740001750528
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.07310378800002582,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006380299998909322,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004580760000862938,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004580760000862938
244
  },
245
  "communicator.exchange": {
246
- "total": 0.0655762330000016,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.0655762330000016
250
  },
251
  "steps_from_proto": {
252
- "total": 0.006431449000046996,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004294929995012353,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.006001956000545761,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.006001956000545761
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 245.25558892300842,
271
- "count": 18203,
272
  "is_parallel": true,
273
- "self": 10.398779897999475,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.246553642999743,
277
- "count": 18203,
278
  "is_parallel": true,
279
- "self": 5.246553642999743
280
  },
281
  "communicator.exchange": {
282
- "total": 193.51584178901112,
283
- "count": 18203,
284
  "is_parallel": true,
285
- "self": 193.51584178901112
286
  },
287
  "steps_from_proto": {
288
- "total": 36.09441359299808,
289
- "count": 18203,
290
  "is_parallel": true,
291
- "self": 6.484813412918129,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 29.60960018007995,
295
- "count": 182030,
296
  "is_parallel": true,
297
- "self": 29.60960018007995
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00017802000002120622,
313
  "count": 1,
314
- "self": 0.00017802000002120622,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 458.7752014971038,
324
- "count": 437497,
325
  "is_parallel": true,
326
- "self": 9.64992278710929,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 250.02878089399564,
330
- "count": 437497,
331
  "is_parallel": true,
332
- "self": 249.2222624149956,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.806518479000033,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.806518479000033
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 199.09649781599887,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 79.48694423101233,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 119.60955358498654,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 119.60955358498654
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.16318799900000158,
364
  "count": 1,
365
- "self": 0.0008954439999797614,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.16229255500002182,
369
  "count": 1,
370
- "self": 0.16229255500002182
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.2230117321014404,
6
+ "min": 1.2230117321014404,
7
+ "max": 2.8615801334381104,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10843.2216796875,
12
+ "min": 10843.2216796875,
13
+ "max": 31634.767578125,
14
+ "count": 20
15
+ },
16
+ "SnowballTarget.Environment.EpisodeLength.mean": {
17
+ "value": 199.0,
18
+ "min": 199.0,
19
+ "max": 199.0,
20
+ "count": 20
21
+ },
22
+ "SnowballTarget.Environment.EpisodeLength.sum": {
23
+ "value": 8756.0,
24
+ "min": 8756.0,
25
+ "max": 10945.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Step.mean": {
29
+ "value": 199800.0,
30
+ "min": 9800.0,
31
+ "max": 199800.0,
32
  "count": 20
33
  },
34
  "SnowballTarget.Step.sum": {
35
+ "value": 199800.0,
36
+ "min": 9800.0,
37
+ "max": 199800.0,
38
  "count": 20
39
  },
40
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
41
+ "value": 2.6578848361968994,
42
+ "min": 0.1388860046863556,
43
+ "max": 2.6578848361968994,
44
  "count": 20
45
  },
46
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
47
+ "value": 132.8942413330078,
48
+ "min": 6.805414199829102,
49
+ "max": 132.8942413330078,
50
  "count": 20
51
  },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 26.06,
54
+ "min": 3.306122448979592,
55
+ "max": 26.06,
56
  "count": 20
57
  },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1303.0,
60
+ "min": 162.0,
61
+ "max": 1303.0,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 26.06,
66
+ "min": 3.306122448979592,
67
+ "max": 26.06,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1303.0,
72
+ "min": 162.0,
73
+ "max": 1303.0,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.06663666524086603,
78
+ "min": 0.062078236376857034,
79
+ "max": 0.07542671996177923,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.26654666096346413,
84
+ "min": 0.24831294550742813,
85
+ "max": 0.3654332542928922,
86
  "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.1303019299007514,
90
+ "min": 0.1107853918098936,
91
+ "max": 0.16196015699237,
92
  "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.5212077196030056,
96
+ "min": 0.45419704154425977,
97
+ "max": 0.80980078496185,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 0.00013250009735000013,
102
+ "min": 0.00013250009735000013,
103
+ "max": 0.0048625000027499995,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 0.0005300003894000005,
108
+ "min": 0.0005300003894000005,
109
+ "max": 0.0230750000385,
110
  "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10265,
114
+ "min": 0.10265,
115
+ "max": 0.19725000000000004,
116
  "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.4106,
120
+ "min": 0.4106,
121
+ "max": 0.9615,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00014223500000000013,
126
+ "min": 0.00014223500000000013,
127
+ "max": 0.004862775,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0005689400000000005,
132
+ "min": 0.0005689400000000005,
133
+ "max": 0.023078849999999998,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1695401510",
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 --force",
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": "1695401999"
160
  },
161
+ "total": 489.3164900869997,
162
  "count": 1,
163
+ "self": 0.4249920430011116,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.0627173489992856,
167
  "count": 1,
168
+ "self": 0.0627173489992856
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 488.8287806949993,
172
  "count": 1,
173
+ "self": 0.6065480870856845,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 5.072198931000457,
177
  "count": 1,
178
+ "self": 5.072198931000457
179
  },
180
  "TrainerController.advance": {
181
+ "total": 482.9976769819132,
182
+ "count": 18215,
183
+ "self": 0.3135042810226878,
184
  "children": {
185
  "env_step": {
186
+ "total": 482.6841727008905,
187
+ "count": 18215,
188
+ "self": 329.7428118088865,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 152.63644833307808,
192
+ "count": 18215,
193
+ "self": 2.010919573111096,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 150.62552875996698,
197
+ "count": 18215,
198
+ "self": 150.62552875996698
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.3049125589259347,
204
+ "count": 18215,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 487.00681764308683,
209
+ "count": 18215,
210
  "is_parallel": true,
211
+ "self": 217.11979806996897,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0031566649995511398,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008025640017876867,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002354100997763453,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002354100997763453
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0503288039999461,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00044396799967216793,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00036525100040307734,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00036525100040307734
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.04633746699983021,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.04633746699983021
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0031821180000406457,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0013967680006317096,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0017853499994089361,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0017853499994089361
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 269.88701957311787,
271
+ "count": 18214,
272
  "is_parallel": true,
273
+ "self": 11.017855447158581,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.760899235985562,
277
+ "count": 18214,
278
  "is_parallel": true,
279
+ "self": 5.760899235985562
280
  },
281
  "communicator.exchange": {
282
+ "total": 213.35939599697667,
283
+ "count": 18214,
284
  "is_parallel": true,
285
+ "self": 213.35939599697667
286
  },
287
  "steps_from_proto": {
288
+ "total": 39.74886889299705,
289
+ "count": 18214,
290
  "is_parallel": true,
291
+ "self": 7.288212614084841,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 32.46065627891221,
295
+ "count": 182140,
296
  "is_parallel": true,
297
+ "self": 32.46065627891221
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 3.9815999116399325e-05,
313
  "count": 1,
314
+ "self": 3.9815999116399325e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 480.6060743708822,
324
+ "count": 287816,
325
  "is_parallel": true,
326
+ "self": 7.188309569088233,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 171.0720139917994,
330
+ "count": 287816,
331
  "is_parallel": true,
332
+ "self": 170.23745129379859,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.8345626980008092,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.8345626980008092
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 302.34575080999457,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 97.19458248201772,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 205.15116832797685,
350
+ "count": 4590,
351
  "is_parallel": true,
352
+ "self": 205.15116832797685
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.152316879000864,
364
  "count": 1,
365
+ "self": 0.0010705269996833522,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.15124635200118064,
369
  "count": 1,
370
+ "self": 0.15124635200118064
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,58 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.363636363636363,
8
- "creation_time": 1695394553.3457396,
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": 20.454545454545453,
17
- "creation_time": 1695394670.3220997,
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": 23.727272727272727,
26
- "creation_time": 1695394785.4409354,
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": 24.272727272727273,
35
- "creation_time": 1695394900.5425246,
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": 24.272727272727273,
44
- "creation_time": 1695394900.7377973,
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": 24.272727272727273,
54
- "creation_time": 1695394900.7377973,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 49800,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49800.onnx",
7
+ "reward": 14.142857142857142,
8
+ "creation_time": 1695401633.3461013,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49800.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 99800,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99800.onnx",
16
+ "reward": 21.0,
17
+ "creation_time": 1695401757.3653636,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99800.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 149800,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149800.onnx",
25
+ "reward": 23.0,
26
+ "creation_time": 1695401883.1586978,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149800.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 199800,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199800.onnx",
34
+ "reward": 26.0,
35
+ "creation_time": 1695401998.799362,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199800.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 200200,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
+ "reward": 26.09090909090909,
44
+ "creation_time": 1695401999.0192761,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
+ "steps": 200200,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 26.09090909090909,
54
+ "creation_time": 1695401999.0192761,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },