Hugging Face's logo

ammr
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
ammr commited on
Commit
44c12c9
·
1 Parent(s): efceb3b

addsnowballtarget

Browse files
Files changed (28) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249944.onnx} +2 -2
  7. SnowballTarget/SnowballTarget-249944.pt +3 -0
  8. SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-299968.onnx} +2 -2
  9. SnowballTarget/SnowballTarget-299968.pt +3 -0
  10. SnowballTarget/SnowballTarget-349992.onnx +3 -0
  11. SnowballTarget/SnowballTarget-349992.pt +3 -0
  12. SnowballTarget/SnowballTarget-399992.onnx +3 -0
  13. SnowballTarget/SnowballTarget-399992.pt +3 -0
  14. SnowballTarget/SnowballTarget-449952.onnx +3 -0
  15. SnowballTarget/SnowballTarget-449952.pt +3 -0
  16. SnowballTarget/SnowballTarget-499976.onnx +3 -0
  17. SnowballTarget/SnowballTarget-499976.pt +3 -0
  18. SnowballTarget/SnowballTarget-500104.onnx +3 -0
  19. SnowballTarget/SnowballTarget-500104.pt +3 -0
  20. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  21. SnowballTarget/SnowballTarget-99960.pt +2 -2
  22. SnowballTarget/checkpoint.pt +2 -2
  23. SnowballTarget/{events.out.tfevents.1678035795.8cac745c4078.6559.0 → events.out.tfevents.1678036777.8cac745c4078.10888.0} +2 -2
  24. config.json +1 -1
  25. configuration.yaml +4 -4
  26. run_logs/Player-0.log +14 -14
  27. run_logs/timers.json +157 -157
  28. run_logs/training_status.json +69 -24
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a211d604995ede8e5eb3cb3dc9eca2fc377a51dc8c7a0bec2dac53dbde9ba7ea
3
- size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1efd375548a462f664c18aae7e46ad8b73f5f5bbe4ad27374316203d8b86ce8
3
+ size 2861403
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76b03b4504c8ed32c0533476fa9f10339f51d93753a89ecec00350dbbb0ae94c
3
- size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a035b952b98c2b7613c47de90ab0fb471faaa7d1e14a89ed88bbb969158d2674
3
+ size 2861403
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6863ee3eb2886586a35d004afdadfe2e8f95d41a994016fac30da9a4c8b2303
3
- size 3845582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11d74aa1a3e014c2a9dfdbf299e010369b4cbad6078e90a9a08c17a105d068f
3
+ size 17123956
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a211d604995ede8e5eb3cb3dc9eca2fc377a51dc8c7a0bec2dac53dbde9ba7ea
3
- size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5c5de796b1360fe7052c7dfe5c4b9954f07b7f637ced61c443975c4e7eb375
3
+ size 2861403
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fee661f793dde6360db1caf33a80112d384cc65fa399cdac6263bf126eed5e9
3
- size 3845582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f900bb9d14cbb39ddd376691bbb6f9bbb276560a41b1eaec5ed0bae21694306
3
+ size 17123956
SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249944.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ed1406acad3dda42b20ecfedd83635034b8bf20d4250df62f88912f36b30b0f
3
- size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3125a6194b4b567b5b8e7388e4e40b263bddecdaecf76b450b917e8cf12b47bc
3
+ size 2861403
SnowballTarget/SnowballTarget-249944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ff65a45f27e03f0bf02d1e091041d544d3409aab4fa7d052627f16fa7ba22e
3
+ size 17123956
SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-299968.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf5eb4d22c768e920ebfcdef67356d281fdde2d3596dbbe42e2cfda20f2adbfe
3
- size 3845582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc7b6833638ea3a492ca99e38962de62998bb3288f15e96e4d28834f7199cea
3
+ size 2861403
SnowballTarget/SnowballTarget-299968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d751097db7ff5f6e78b066f59eff897aa06e02b08b50bdfbe4a62d20004c2099
3
+ size 17123956
SnowballTarget/SnowballTarget-349992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb93419afc3182ecb77795086ce489425bef75a4d3d843861070f73724e8d2f
3
+ size 2861403
SnowballTarget/SnowballTarget-349992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f9d34cd91184d817777e273685c51c2eb36879a967ee4cdc8656901b9ceef4
3
+ size 17123956
SnowballTarget/SnowballTarget-399992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297cd8bb40785d811ca80ae076bb60be6456a7e45c6c206ed6e9f0c9a819b103
3
+ size 2861403
SnowballTarget/SnowballTarget-399992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c83d8a533cabac2bb9972232268898d6cae13a0c05a71a489e42b8758c327b
3
+ size 17123956
SnowballTarget/SnowballTarget-449952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b959cad20be734e641545e203066bac0606d98917b8afd2d60ec35e2ad438b75
3
+ size 2861403
SnowballTarget/SnowballTarget-449952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e2a2a7a8eb7c12877869466928c022f7c7ce31a61f08f106d4edfae357727f
3
+ size 17123956
SnowballTarget/SnowballTarget-499976.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1efd375548a462f664c18aae7e46ad8b73f5f5bbe4ad27374316203d8b86ce8
3
+ size 2861403
SnowballTarget/SnowballTarget-499976.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b76cdb7435f493139afc3f85dfd263d7d1f282df8ed0a0de713fdde0da9cfb
3
+ size 17123956
SnowballTarget/SnowballTarget-500104.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1efd375548a462f664c18aae7e46ad8b73f5f5bbe4ad27374316203d8b86ce8
3
+ size 2861403
SnowballTarget/SnowballTarget-500104.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6389af4f8a47b45eb17753aad2b30eef29a877ef443231e1f20008effb6377
3
+ size 17123956
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f0cced6ea41fcd181a20bdbcc43f2277106036f9664f7f2a88b928dcd800adb
3
- size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e013fb9851fa86ca5fbb5bab52c8c1e2e42f6ed7cb38537fe11472e919650dbe
3
+ size 2861403
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdf3fa39891ac28aa9860325dae393a45d4031e9a831f3357bac86d51d3329cb
3
- size 3845582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee80e8278f0eba688550af56b204f6feed46d868fcc7971122ba0630d6f1063a
3
+ size 17123956
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9ad410d79b14e251b5abbac09fcb4481d8f3b610854dbccaa6469f3d8157ece
3
- size 3845582
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6389af4f8a47b45eb17753aad2b30eef29a877ef443231e1f20008effb6377
3
+ size 17123956
SnowballTarget/{events.out.tfevents.1678035795.8cac745c4078.6559.0 → events.out.tfevents.1678036777.8cac745c4078.10888.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:433036b92a5b8a3bbfb9ee98dcd635b00d3f6a6cd8bb47de3c1823f6ca0a9843
3
- size 24633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6911a5f57e786d6c7bfdeaccfdd0a775f62c72354801bf69bfcacb46f8afe95
3
+ size 81600
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "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": true, "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": 1e-05, "beta": 0.005, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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, "checkpoint_interval": 50000, "max_steps": 500000, "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": 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: 0.0001
9
  beta: 0.005
10
  epsilon: 0.1
11
  lambd: 0.95
@@ -15,8 +15,8 @@ behaviors:
15
  epsilon_schedule: linear
16
  network_settings:
17
  normalize: false
18
- hidden_units: 256
19
- num_layers: 2
20
  vis_encode_type: simple
21
  memory: null
22
  goal_conditioning_type: hyper
@@ -36,7 +36,7 @@ behaviors:
36
  init_path: null
37
  keep_checkpoints: 10
38
  checkpoint_interval: 50000
39
- max_steps: 200000
40
  time_horizon: 64
41
  summary_freq: 10000
42
  threaded: true
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 1.0e-05
9
  beta: 0.005
10
  epsilon: 0.1
11
  lambd: 0.95
 
15
  epsilon_schedule: linear
16
  network_settings:
17
  normalize: false
18
+ hidden_units: 512
19
+ num_layers: 3
20
  vis_encode_type: simple
21
  memory: null
22
  goal_conditioning_type: hyper
 
36
  init_path: null
37
  keep_checkpoints: 10
38
  checkpoint_interval: 50000
39
+ max_steps: 500000
40
  time_horizon: 64
41
  summary_freq: 10000
42
  threaded: true
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.082 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)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
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: 0.642188 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.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5371 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
@@ -172,16 +172,16 @@ Memory Statistics:
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]: 5463 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 7.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 17.4 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
@@ -210,13 +210,13 @@ Memory Statistics:
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]: 3766 frames, [64.0 KB-128.0 KB]: 1697 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
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]: 5463 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]: 5462 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
@@ -246,13 +246,13 @@ Memory Statistics:
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]: 5463 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]: 5463 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.081 seconds
35
  ERROR: Shader 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: 0.641403 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]: 13417 frames, [16.0 KB-32.0 KB]: 227 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
 
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]: 10979 frames, [8.0 MB-16.0 MB]: 2666 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13645 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 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]: 7610 frames, [64.0 KB-128.0 KB]: 6035 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.7 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13645 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]: 13645 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]: 13644 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]: 13645 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]: 13645 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
@@ -2,153 +2,153 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.4694273471832275,
6
- "min": 1.4694273471832275,
7
- "max": 2.877119541168213,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 14110.9111328125,
12
- "min": 14110.9111328125,
13
- "max": 29559.52734375,
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": 9.996574401855469,
30
- "min": 0.37617459893226624,
31
- "max": 9.996574401855469,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1949.33203125,
36
- "min": 72.97787475585938,
37
- "max": 2004.43212890625,
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": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.06617252733507056,
54
- "min": 0.06253673741004925,
55
- "max": 0.07420266700329889,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.26469010934028225,
60
- "min": 0.250146949640197,
61
- "max": 0.3511263588024603,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2408758353222819,
66
- "min": 0.11121187233982388,
67
- "max": 0.26978057647452636,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.9635033412891276,
72
- "min": 0.4448474893592955,
73
- "max": 1.3489028823726317,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 2.6940973060000016e-06,
78
- "min": 2.6940973060000016e-06,
79
- "max": 9.729400270600002e-05,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.0776389224000007e-05,
84
- "min": 1.0776389224000007e-05,
85
- "max": 0.00046172003828000015,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
  "value": 0.09999999999999998,
90
  "min": 0.09999999999999998,
91
  "max": 0.09999999999999998,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.3999999999999999,
96
  "min": 0.3999999999999999,
97
  "max": 0.4999999999999999,
98
- "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
- "value": 0.0001444306000000001,
102
- "min": 0.0001444306000000001,
103
- "max": 0.004864970599999999,
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": 19.886363636363637,
114
- "min": 2.8636363636363638,
115
- "max": 19.886363636363637,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 875.0,
120
- "min": 126.0,
121
- "max": 1091.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 19.886363636363637,
126
- "min": 2.8636363636363638,
127
- "max": 19.886363636363637,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 875.0,
132
- "min": 126.0,
133
- "max": 1091.0,
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": "1678035791",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
@@ -156,66 +156,66 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
- "end_time_seconds": "1678036335"
160
  },
161
- "total": 543.5649645139999,
162
  "count": 1,
163
- "self": 0.785157985000069,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10759228999995685,
167
  "count": 1,
168
- "self": 0.10759228999995685
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 542.6722142389999,
172
  "count": 1,
173
- "self": 0.5381760530101474,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 6.928671871999995,
177
  "count": 1,
178
- "self": 6.928671871999995
179
  },
180
  "TrainerController.advance": {
181
- "total": 534.9940004429898,
182
- "count": 18210,
183
- "self": 0.27205131597474974,
184
  "children": {
185
  "env_step": {
186
- "total": 534.721949127015,
187
- "count": 18210,
188
- "self": 385.2726056480435,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 149.1597922129954,
192
- "count": 18210,
193
- "self": 1.5831741370018335,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 147.57661807599357,
197
- "count": 18210,
198
- "self": 32.80984432500395,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
- "total": 114.76677375098961,
202
- "count": 18210,
203
- "self": 114.76677375098961
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
- "total": 0.28955126597611525,
211
- "count": 18210,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
- "total": 541.0359419470033,
216
- "count": 18210,
217
  "is_parallel": true,
218
- "self": 291.9733024630241,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
@@ -224,48 +224,48 @@
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
- "total": 0.0022754120000172406,
228
  "count": 1,
229
  "is_parallel": true,
230
- "self": 0.0007699310003772553,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
- "total": 0.0015054809996399854,
234
  "count": 10,
235
  "is_parallel": true,
236
- "self": 0.0015054809996399854
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
- "total": 0.05132571000012831,
242
  "count": 1,
243
  "is_parallel": true,
244
- "self": 0.0006334280001283332,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
- "total": 0.0004171319999386469,
248
  "count": 1,
249
  "is_parallel": true,
250
- "self": 0.0004171319999386469
251
  },
252
  "communicator.exchange": {
253
- "total": 0.04818544599993402,
254
  "count": 1,
255
  "is_parallel": true,
256
- "self": 0.04818544599993402
257
  },
258
  "steps_from_proto": {
259
- "total": 0.0020897040001273126,
260
  "count": 1,
261
  "is_parallel": true,
262
- "self": 0.0005734110000048531,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
- "total": 0.0015162930001224595,
266
  "count": 10,
267
  "is_parallel": true,
268
- "self": 0.0015162930001224595
269
  }
270
  }
271
  }
@@ -274,34 +274,34 @@
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
- "total": 249.06263948397918,
278
- "count": 18209,
279
  "is_parallel": true,
280
- "self": 9.97293427995669,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
- "total": 5.687937014006593,
284
- "count": 18209,
285
  "is_parallel": true,
286
- "self": 5.687937014006593
287
  },
288
  "communicator.exchange": {
289
- "total": 199.5349575030209,
290
- "count": 18209,
291
  "is_parallel": true,
292
- "self": 199.5349575030209
293
  },
294
  "steps_from_proto": {
295
- "total": 33.866810686994995,
296
- "count": 18209,
297
  "is_parallel": true,
298
- "self": 7.550632629977827,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
- "total": 26.31617805701717,
302
- "count": 182090,
303
  "is_parallel": true,
304
- "self": 26.31617805701717
305
  }
306
  }
307
  }
@@ -316,9 +316,9 @@
316
  }
317
  },
318
  "trainer_threads": {
319
- "total": 0.00013248899995232932,
320
  "count": 1,
321
- "self": 0.00013248899995232932,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,36 +327,36 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 531.2292537309627,
331
- "count": 410466,
332
  "is_parallel": true,
333
- "self": 11.0115854399196,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 271.62298273604074,
337
- "count": 410466,
338
  "is_parallel": true,
339
- "self": 270.561674838041,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
- "total": 1.061307897999768,
343
- "count": 4,
344
  "is_parallel": true,
345
- "self": 1.061307897999768
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
- "total": 248.59468555500234,
351
- "count": 90,
352
  "is_parallel": true,
353
- "self": 97.310092754994,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
- "total": 151.28459280000834,
357
- "count": 7645,
358
  "is_parallel": true,
359
- "self": 151.28459280000834
360
  }
361
  }
362
  }
@@ -367,14 +367,14 @@
367
  }
368
  },
369
  "TrainerController._save_models": {
370
- "total": 0.21123338200004582,
371
  "count": 1,
372
- "self": 0.002096945999937816,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
- "total": 0.209136436000108,
376
  "count": 1,
377
- "self": 0.209136436000108
378
  }
379
  }
380
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.379467248916626,
6
+ "min": 1.3658976554870605,
7
+ "max": 2.8902292251586914,
8
+ "count": 50
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 13338.0693359375,
12
+ "min": 13149.9287109375,
13
+ "max": 29806.396484375,
14
+ "count": 50
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499976.0,
18
  "min": 9952.0,
19
+ "max": 499976.0,
20
+ "count": 50
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499976.0,
24
  "min": 9952.0,
25
+ "max": 499976.0,
26
+ "count": 50
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 8.437034606933594,
30
+ "min": 0.36532363295555115,
31
+ "max": 8.467759132385254,
32
+ "count": 50
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1729.592041015625,
36
+ "min": 70.87278747558594,
37
+ "max": 1729.592041015625,
38
+ "count": 50
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 50
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 50
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06762183531892815,
54
+ "min": 0.06283424676546608,
55
+ "max": 0.07704412460255243,
56
+ "count": 50
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3381091765946408,
60
+ "min": 0.2513369870618643,
61
+ "max": 0.38522062301276216,
62
+ "count": 50
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2600751572847366,
66
+ "min": 0.09842146840425867,
67
+ "max": 0.2953235766466926,
68
+ "count": 50
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 1.3003757864236831,
72
+ "min": 0.39368587361703467,
73
+ "max": 1.4757395293782738,
74
+ "count": 50
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.0185898240000011e-07,
78
+ "min": 1.0185898240000011e-07,
79
+ "max": 9.891761082400001e-06,
80
+ "count": 50
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 5.092949120000005e-07,
84
+ "min": 5.092949120000005e-07,
85
+ "max": 4.846881531200001e-05,
86
+ "count": 50
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
  "value": 0.09999999999999998,
90
  "min": 0.09999999999999998,
91
  "max": 0.09999999999999998,
92
+ "count": 50
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.4999999999999999,
96
  "min": 0.3999999999999999,
97
  "max": 0.4999999999999999,
98
+ "count": 50
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.0778240000000044e-05,
102
+ "min": 6.0778240000000044e-05,
103
+ "max": 0.00494598824,
104
+ "count": 50
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003038912000000002,
108
+ "min": 0.0003038912000000002,
109
+ "max": 0.0242359312,
110
+ "count": 50
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 16.654545454545456,
114
+ "min": 2.7954545454545454,
115
+ "max": 16.933333333333334,
116
+ "count": 50
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 916.0,
120
+ "min": 123.0,
121
+ "max": 916.0,
122
+ "count": 50
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 16.654545454545456,
126
+ "min": 2.7954545454545454,
127
+ "max": 16.933333333333334,
128
+ "count": 50
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 916.0,
132
+ "min": 123.0,
133
+ "max": 916.0,
134
+ "count": 50
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 50
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 50
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1678036774",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
+ "end_time_seconds": "1678038129"
160
  },
161
+ "total": 1355.2741498350001,
162
  "count": 1,
163
+ "self": 0.42571783100038374,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10620994700002484,
167
  "count": 1,
168
+ "self": 0.10620994700002484
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1354.7422220569997,
172
  "count": 1,
173
+ "self": 1.2987555020931723,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 6.9214117719998285,
177
  "count": 1,
178
+ "self": 6.9214117719998285
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1346.3238731689066,
182
+ "count": 45481,
183
+ "self": 0.6902974328422715,
184
  "children": {
185
  "env_step": {
186
+ "total": 1345.6335757360644,
187
+ "count": 45481,
188
+ "self": 978.0263863250761,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 366.90428748296654,
192
+ "count": 45481,
193
+ "self": 3.8421440909337434,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 363.0621433920328,
197
+ "count": 45481,
198
+ "self": 81.0664011170361,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
+ "total": 281.9957422749967,
202
+ "count": 45481,
203
+ "self": 281.9957422749967
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
+ "total": 0.7029019280216744,
211
+ "count": 45481,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
+ "total": 1350.7219736509523,
216
+ "count": 45481,
217
  "is_parallel": true,
218
+ "self": 745.7596506200007,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
 
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
+ "total": 0.002202131999638368,
228
  "count": 1,
229
  "is_parallel": true,
230
+ "self": 0.0007464009995601373,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
+ "total": 0.0014557310000782309,
234
  "count": 10,
235
  "is_parallel": true,
236
+ "self": 0.0014557310000782309
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
+ "total": 0.12093137900001238,
242
  "count": 1,
243
  "is_parallel": true,
244
+ "self": 0.0005905819998588413,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0003977070000473759,
248
  "count": 1,
249
  "is_parallel": true,
250
+ "self": 0.0003977070000473759
251
  },
252
  "communicator.exchange": {
253
+ "total": 0.11782462200017108,
254
  "count": 1,
255
  "is_parallel": true,
256
+ "self": 0.11782462200017108
257
  },
258
  "steps_from_proto": {
259
+ "total": 0.002118467999935092,
260
  "count": 1,
261
  "is_parallel": true,
262
+ "self": 0.0005638190000354371,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
+ "total": 0.0015546489998996549,
266
  "count": 10,
267
  "is_parallel": true,
268
+ "self": 0.0015546489998996549
269
  }
270
  }
271
  }
 
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
+ "total": 604.9623230309517,
278
+ "count": 45480,
279
  "is_parallel": true,
280
+ "self": 24.243029215894694,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
+ "total": 14.017686898082047,
284
+ "count": 45480,
285
  "is_parallel": true,
286
+ "self": 14.017686898082047
287
  },
288
  "communicator.exchange": {
289
+ "total": 484.74032751698724,
290
+ "count": 45480,
291
  "is_parallel": true,
292
+ "self": 484.74032751698724
293
  },
294
  "steps_from_proto": {
295
+ "total": 81.96127939998769,
296
+ "count": 45480,
297
  "is_parallel": true,
298
+ "self": 17.794618126076784,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
+ "total": 64.1666612739109,
302
+ "count": 454800,
303
  "is_parallel": true,
304
+ "self": 64.1666612739109
305
  }
306
  }
307
  }
 
316
  }
317
  },
318
  "trainer_threads": {
319
+ "total": 4.2113999825232895e-05,
320
  "count": 1,
321
+ "self": 4.2113999825232895e-05,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
 
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
+ "total": 1337.9136293721012,
331
+ "count": 990341,
332
  "is_parallel": true,
333
+ "self": 25.311831634034206,
334
  "children": {
335
  "process_trajectory": {
336
+ "total": 663.8091825050647,
337
+ "count": 990341,
338
  "is_parallel": true,
339
+ "self": 659.3907684300657,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
+ "total": 4.418414074998964,
343
+ "count": 10,
344
  "is_parallel": true,
345
+ "self": 4.418414074998964
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
+ "total": 648.7926152330024,
351
+ "count": 227,
352
  "is_parallel": true,
353
+ "self": 261.1463918159725,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
+ "total": 387.6462234170299,
357
+ "count": 19290,
358
  "is_parallel": true,
359
+ "self": 387.6462234170299
360
  }
361
  }
362
  }
 
367
  }
368
  },
369
  "TrainerController._save_models": {
370
+ "total": 0.19813950000025216,
371
  "count": 1,
372
+ "self": 0.00316469400013375,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
+ "total": 0.1949748060001184,
376
  "count": 1,
377
+ "self": 0.1949748060001184
378
  }
379
  }
380
  }
run_logs/training_status.json CHANGED
@@ -1,20 +1,11 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 9.0,
8
- "creation_time": 1678035931.8002622,
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": 16.09090909090909,
17
- "creation_time": 1678036066.813796,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +13,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 16.181818181818183,
26
- "creation_time": 1678036201.2113643,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,29 +22,83 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 19.636363636363637,
35
- "creation_time": 1678036334.4560852,
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": 19.636363636363637,
44
- "creation_time": 1678036334.7086399,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 19.636363636363637,
54
- "creation_time": 1678036334.7086399,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 99960,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
7
+ "reward": 9.272727272727273,
8
+ "creation_time": 1678037054.6469975,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
11
  ]
 
13
  {
14
  "steps": 149984,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
16
+ "reward": 10.727272727272727,
17
+ "creation_time": 1678037190.032002,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
20
  ]
 
22
  {
23
  "steps": 199984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
25
+ "reward": 12.818181818181818,
26
+ "creation_time": 1678037323.5053747,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249944,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
34
+ "reward": 14.818181818181818,
35
+ "creation_time": 1678037458.7937732,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299968,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
43
+ "reward": 13.363636363636363,
44
+ "creation_time": 1678037594.9936123,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349992,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
52
+ "reward": 16.363636363636363,
53
+ "creation_time": 1678037729.5307827,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399992,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
61
+ "reward": 17.454545454545453,
62
+ "creation_time": 1678037861.8244336,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449952,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
70
+ "reward": 16.90909090909091,
71
+ "creation_time": 1678037994.668055,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499976,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
79
+ "reward": 14.818181818181818,
80
+ "creation_time": 1678038128.7997293,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500104,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
88
+ "reward": 14.818181818181818,
89
+ "creation_time": 1678038129.0271752,
90
  "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500104,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 14.818181818181818,
99
+ "creation_time": 1678038129.0271752,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
102
  ]
103
  }
104
  },