Hugging Face's logo

juansebashr
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
juansebashr commited on
Commit
bc77f53
·
1 Parent(s): 150cca0

Second Push

Browse files
Files changed (22) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249973.onnx} +1 -1
  3. SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249973.pt} +2 -2
  4. SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-299997.onnx} +1 -1
  5. SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-299997.pt} +2 -2
  6. SnowballTarget/SnowballTarget-349957.onnx +3 -0
  7. SnowballTarget/SnowballTarget-349957.pt +3 -0
  8. SnowballTarget/SnowballTarget-399957.onnx +3 -0
  9. SnowballTarget/SnowballTarget-399957.pt +3 -0
  10. SnowballTarget/SnowballTarget-449981.onnx +3 -0
  11. SnowballTarget/SnowballTarget-449981.pt +3 -0
  12. SnowballTarget/SnowballTarget-499941.onnx +3 -0
  13. SnowballTarget/SnowballTarget-499941.pt +3 -0
  14. SnowballTarget/SnowballTarget-500005.onnx +3 -0
  15. SnowballTarget/SnowballTarget-500005.pt +3 -0
  16. SnowballTarget/checkpoint.pt +1 -1
  17. SnowballTarget/events.out.tfevents.1678766969.DESKTOP-3TN0IDS.1955.0 +3 -0
  18. config.json +1 -1
  19. configuration.yaml +3 -3
  20. run_logs/Player-0.log +15 -15
  21. run_logs/timers.json +166 -364
  22. run_logs/training_status.json +67 -22
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376efdcabb2908a49d39a08ea4e01434b6b971f1e3c3c5f5e606d21b9ac5423d
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2440027ffef68dd368dbf6da273be9d96033a5ad45731797958f38f2d703cafd
3
  size 650646
SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-249973.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d88e7a7730ce67995eaf9242049c9af3e40ac8c253fddac49820de51f577c690
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279d382cfd5b8f354446f5f298f4352b268fdcfe330dad98fb38ee211e006350
3
  size 650646
SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-249973.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c02b88f3d7cfe4bae1e37e20ed2c85f0cd9ab9ba6cc348f1868ce3019a4475
3
- size 3849541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30fc1b36d2afbbc536ebe2b37525e781265411f34b2d2863eeae0449a2bca4a2
3
+ size 3849614
SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-299997.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c21fc68b7ffe0f658f71d5f34531dd32ad419507bf3353372fd7110a4e9535f
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7190df2e45d19ac42607066c38ce755328e02d6af3b622382a6d104a094082c
3
  size 650646
SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-299997.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c14af893c46b9fcdcd82c3dc7ed429701505478de418f91f80de733546b6279
3
- size 3849541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b4f03305513f7886af485d9fb87df103e85808251ad76b49d13ce6a7b224c9
3
+ size 3849614
SnowballTarget/SnowballTarget-349957.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64cd8c8cc157e8a57740a329b96400d7a984a91d65b23ec5ccb75ccf392151f0
3
+ size 650646
SnowballTarget/SnowballTarget-349957.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe3869d171ed07588c66c5061af5320fd5961cf007e488c27296c02cf1de99a
3
+ size 3849614
SnowballTarget/SnowballTarget-399957.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130d896a7e5763531dff6b4f542234c7853b729364c0fe3272eee10824bc7410
3
+ size 650646
SnowballTarget/SnowballTarget-399957.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c003062238a3b291cd42e391fdc835420fb9eeb815468decaf9f17530ffeca
3
+ size 3849614
SnowballTarget/SnowballTarget-449981.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a02cd9d91f49bef38247af64ad0fbbe14bf30549a73122b92dfef6200bcd45
3
+ size 650646
SnowballTarget/SnowballTarget-449981.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027393923a6097bb028df98db8d63b1741600fa9cda908f42b365ad71924c2bb
3
+ size 3849614
SnowballTarget/SnowballTarget-499941.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2440027ffef68dd368dbf6da273be9d96033a5ad45731797958f38f2d703cafd
3
+ size 650646
SnowballTarget/SnowballTarget-499941.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e61a3745bcaa45f8cf506d56db77d779e54c81b34e0d971e96f7566753988e7
3
+ size 3849614
SnowballTarget/SnowballTarget-500005.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2440027ffef68dd368dbf6da273be9d96033a5ad45731797958f38f2d703cafd
3
+ size 650646
SnowballTarget/SnowballTarget-500005.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57c232cdf5cc499447257942a659de4a1fed56e83525eb1e8ee2537cdf99c70
3
+ size 3849614
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08d5b9a788096f2e88b11bffd1729d199ff5dda7b36e314e2f4a8d56f8ca1ff
3
  size 3848811
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a294ef004f08cebc2598cd5f1b593c476000c622be38cb8478ae4ce6cb578af3
3
  size 3848811
SnowballTarget/events.out.tfevents.1678766969.DESKTOP-3TN0IDS.1955.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37db546fa8c3b5ca3d2de1df3b69cfa1389c89ae2ea457355c5ec6d1ef823dce
3
+ size 25999
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/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": 256, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -67,8 +67,8 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
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
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
+ force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
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 0.046 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: 0.527656 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 8 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]: 2501 frames, [16.0 KB-32.0 KB]: 42 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
@@ -236,22 +236,22 @@ Memory Statistics:
236
  Peak Allocated Bytes 0 B
237
  Overflow Count 0
238
  [ALLOC_DEFAULT] Dual Thread Allocator
239
- Peak main deferred allocation count 38
240
  [ALLOC_BUCKET]
241
  Large Block size 4.0 MB
242
  Used Block count 1
243
  Peak Allocated bytes 1.0 MB
244
  [ALLOC_DEFAULT_MAIN]
245
- Peak usage frame count: [4.0 MB-8.0 MB]: 2544 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
- Peak Allocated memory 6.1 MB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_DEFAULT_THREAD]
251
- Peak usage frame count: [16.0 MB-32.0 MB]: 2544 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
- Peak Allocated memory 17.5 MB
255
  Peak Large allocation bytes 16.0 MB
256
  [ALLOC_TEMP_JOB_1_FRAME]
257
  Initial Block Size 2.0 MB
@@ -280,13 +280,13 @@ Memory Statistics:
280
  Used Block count 1
281
  Peak Allocated bytes 1.0 MB
282
  [ALLOC_GFX_MAIN]
283
- Peak usage frame count: [32.0 KB-64.0 KB]: 1713 frames, [64.0 KB-128.0 KB]: 831 frames
284
  Requested Block Size 16.0 MB
285
  Peak Block count 1
286
- Peak Allocated memory 66.8 KB
287
  Peak Large allocation bytes 0 B
288
  [ALLOC_GFX_THREAD]
289
- Peak usage frame count: [32.0 KB-64.0 KB]: 2544 frames
290
  Requested Block Size 16.0 MB
291
  Peak Block count 1
292
  Peak Allocated memory 39.6 KB
@@ -298,13 +298,13 @@ Memory Statistics:
298
  Used Block count 1
299
  Peak Allocated bytes 1.0 MB
300
  [ALLOC_CACHEOBJECTS_MAIN]
301
- Peak usage frame count: [0.5 MB-1.0 MB]: 2544 frames
302
  Requested Block Size 4.0 MB
303
  Peak Block count 1
304
  Peak Allocated memory 0.6 MB
305
  Peak Large allocation bytes 0 B
306
  [ALLOC_CACHEOBJECTS_THREAD]
307
- Peak usage frame count: [0.5 MB-1.0 MB]: 2543 frames, [2.0 MB-4.0 MB]: 1 frames
308
  Requested Block Size 4.0 MB
309
  Peak Block count 1
310
  Peak Allocated memory 2.2 MB
@@ -316,13 +316,13 @@ Memory Statistics:
316
  Used Block count 1
317
  Peak Allocated bytes 1.0 MB
318
  [ALLOC_TYPETREE_MAIN]
319
- Peak usage frame count: [0-1.0 KB]: 2544 frames
320
  Requested Block Size 2.0 MB
321
  Peak Block count 1
322
  Peak Allocated memory 1.0 KB
323
  Peak Large allocation bytes 0 B
324
  [ALLOC_TYPETREE_THREAD]
325
- Peak usage frame count: [1.0 KB-2.0 KB]: 2544 frames
326
  Requested Block Size 2.0 MB
327
  Peak Block count 1
328
  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 0.071 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: 0.787898 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 8 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]: 8046 frames, [16.0 KB-32.0 KB]: 136 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
 
236
  Peak Allocated Bytes 0 B
237
  Overflow Count 0
238
  [ALLOC_DEFAULT] Dual Thread Allocator
239
+ Peak main deferred allocation count 36
240
  [ALLOC_BUCKET]
241
  Large Block size 4.0 MB
242
  Used Block count 1
243
  Peak Allocated bytes 1.0 MB
244
  [ALLOC_DEFAULT_MAIN]
245
+ Peak usage frame count: [4.0 MB-8.0 MB]: 8183 frames
246
  Requested Block Size 16.0 MB
247
  Peak Block count 1
248
+ Peak Allocated memory 7.8 MB
249
  Peak Large allocation bytes 0 B
250
  [ALLOC_DEFAULT_THREAD]
251
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8183 frames
252
  Requested Block Size 16.0 MB
253
  Peak Block count 1
254
+ Peak Allocated memory 17.4 MB
255
  Peak Large allocation bytes 16.0 MB
256
  [ALLOC_TEMP_JOB_1_FRAME]
257
  Initial Block Size 2.0 MB
 
280
  Used Block count 1
281
  Peak Allocated bytes 1.0 MB
282
  [ALLOC_GFX_MAIN]
283
+ Peak usage frame count: [32.0 KB-64.0 KB]: 7680 frames, [64.0 KB-128.0 KB]: 503 frames
284
  Requested Block Size 16.0 MB
285
  Peak Block count 1
286
+ Peak Allocated memory 66.4 KB
287
  Peak Large allocation bytes 0 B
288
  [ALLOC_GFX_THREAD]
289
+ Peak usage frame count: [32.0 KB-64.0 KB]: 8183 frames
290
  Requested Block Size 16.0 MB
291
  Peak Block count 1
292
  Peak Allocated memory 39.6 KB
 
298
  Used Block count 1
299
  Peak Allocated bytes 1.0 MB
300
  [ALLOC_CACHEOBJECTS_MAIN]
301
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8183 frames
302
  Requested Block Size 4.0 MB
303
  Peak Block count 1
304
  Peak Allocated memory 0.6 MB
305
  Peak Large allocation bytes 0 B
306
  [ALLOC_CACHEOBJECTS_THREAD]
307
+ Peak usage frame count: [0.5 MB-1.0 MB]: 8182 frames, [2.0 MB-4.0 MB]: 1 frames
308
  Requested Block Size 4.0 MB
309
  Peak Block count 1
310
  Peak Allocated memory 2.2 MB
 
316
  Used Block count 1
317
  Peak Allocated bytes 1.0 MB
318
  [ALLOC_TYPETREE_MAIN]
319
+ Peak usage frame count: [0-1.0 KB]: 8183 frames
320
  Requested Block Size 2.0 MB
321
  Peak Block count 1
322
  Peak Allocated memory 1.0 KB
323
  Peak Large allocation bytes 0 B
324
  [ALLOC_TYPETREE_THREAD]
325
+ Peak usage frame count: [1.0 KB-2.0 KB]: 8183 frames
326
  Requested Block Size 2.0 MB
327
  Peak Block count 1
328
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,263 +2,263 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.008720874786377,
6
- "min": 2.008720874786377,
7
- "max": 2.8902528285980225,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 19444.41796875,
12
- "min": 19444.41796875,
13
- "max": 29662.6640625,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199973.0,
18
- "min": 9952.0,
19
- "max": 199973.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199973.0,
24
- "min": 9952.0,
25
- "max": 199973.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 1.5469045639038086,
30
- "min": -0.040198374539613724,
31
- "max": 1.5469045639038086,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 315.56854248046875,
36
- "min": -7.798484802246094,
37
- "max": 315.56854248046875,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
- "min": 198.75,
43
  "max": 199.0,
44
- "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
- "min": 8745.0,
49
  "max": 10945.0,
50
- "count": 20
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
- "value": 16.036363636363635,
54
- "min": 3.090909090909091,
55
- "max": 16.036363636363635,
56
- "count": 20
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
- "value": 882.0,
60
- "min": 136.0,
61
- "max": 882.0,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
- "value": 16.036363636363635,
66
- "min": 3.090909090909091,
67
- "max": 16.036363636363635,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
- "value": 882.0,
72
- "min": 136.0,
73
- "max": 882.0,
74
- "count": 20
75
  },
76
  "SnowballTarget.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
- "count": 20
81
  },
82
  "SnowballTarget.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
- "count": 20
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
- "value": 0.056310765777570417,
90
- "min": 0.04421131589868829,
91
- "max": 0.05639910812887592,
92
- "count": 19
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
- "value": 0.056310765777570417,
96
- "min": 0.04421131589868829,
97
- "max": 0.05639910812887592,
98
- "count": 19
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
- "value": 0.159035952602114,
102
- "min": 0.06301207421790986,
103
- "max": 0.159035952602114,
104
- "count": 19
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
- "value": 0.159035952602114,
108
- "min": 0.06301207421790986,
109
- "max": 0.159035952602114,
110
- "count": 19
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
- "value": 3.4559965449999866e-07,
114
- "min": 3.4559965449999866e-07,
115
- "max": 9.454400545600001e-05,
116
- "count": 19
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
- "value": 3.4559965449999866e-07,
120
- "min": 3.4559965449999866e-07,
121
- "max": 9.454400545600001e-05,
122
- "count": 19
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
- "value": 0.10034549999999999,
126
- "min": 0.10034549999999999,
127
- "max": 0.19454400000000002,
128
- "count": 19
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
- "value": 0.10034549999999999,
132
- "min": 0.10034549999999999,
133
- "max": 0.19454400000000002,
134
- "count": 19
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
- "value": 2.724044999999993e-05,
138
- "min": 2.724044999999993e-05,
139
- "max": 0.0047277456,
140
- "count": 19
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
- "value": 2.724044999999993e-05,
144
- "min": 2.724044999999993e-05,
145
- "max": 0.0047277456,
146
- "count": 19
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1678764610",
152
  "python_version": "3.9.5 (default, Nov 23 2021, 15:27:38) \n[GCC 9.3.0]",
153
- "command_line_arguments": "/home/sebastian/.virtualenvs/deep_rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/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": "1.13.1+cu117",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1678765032"
160
  },
161
- "total": 422.27248455200015,
162
  "count": 1,
163
- "self": 0.2182025150004847,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.009295840000049793,
167
  "count": 1,
168
- "self": 0.009295840000049793
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 422.0449861969996,
172
  "count": 1,
173
- "self": 0.44254692701133536,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 1.783908978999989,
177
  "count": 1,
178
- "self": 1.783908978999989
179
  },
180
  "TrainerController.advance": {
181
- "total": 419.75098108198836,
182
- "count": 18211,
183
- "self": 0.20495591098551813,
184
  "children": {
185
  "env_step": {
186
- "total": 419.54602517100284,
187
- "count": 18211,
188
- "self": 272.39533732794916,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 146.94134104702016,
192
- "count": 18212,
193
- "self": 1.0576354189834092,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 145.88370562803675,
197
- "count": 18211,
198
- "self": 145.88370562803675
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2093467960335147,
204
- "count": 18211,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 639.9939458850404,
209
- "count": 18211,
210
  "is_parallel": true,
211
- "self": 477.9403825000677,
212
  "children": {
213
  "run_training.setup": {
214
- "total": 0.009295840000049793,
215
- "count": 1,
216
  "is_parallel": true,
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
- "total": 0.0012318619997131464,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0003433719984968775,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0008884900012162689,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0008884900012162689
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.020183925999845087,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00022471199963547406,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00030967300017437083,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00030967300017437083
244
  },
245
  "communicator.exchange": {
246
- "total": 0.018938994000109233,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.018938994000109233
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0007105469999260094,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00016136200065375306,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0005491849992722564,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0005491849992722564
262
  }
263
  }
264
  }
@@ -267,232 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 162.04426754497263,
271
- "count": 18209,
272
  "is_parallel": true,
273
- "self": 4.440110142904814,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 2.593466966046435,
277
- "count": 18209,
278
  "is_parallel": true,
279
- "self": 2.593466966046435
280
  },
281
  "communicator.exchange": {
282
- "total": 141.46004535501334,
283
- "count": 18209,
284
  "is_parallel": true,
285
- "self": 141.46004535501334
286
  },
287
  "steps_from_proto": {
288
- "total": 13.550645081008042,
289
- "count": 18208,
290
  "is_parallel": true,
291
- "self": 2.875771838120272,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 10.67487324288777,
295
- "count": 182080,
296
  "is_parallel": true,
297
- "self": 10.67487324288777
298
- }
299
- }
300
- }
301
- }
302
- },
303
- "TrainerController.start_learning": {
304
- "total": 0.0,
305
- "count": 0,
306
- "is_parallel": true,
307
- "self": 0.0,
308
- "children": {
309
- "TrainerController._reset_env": {
310
- "total": 1.783908978999989,
311
- "count": 1,
312
- "is_parallel": true,
313
- "self": 1.783908978999989
314
- },
315
- "TrainerController.advance": {
316
- "total": 216.72225469500154,
317
- "count": 9734,
318
- "is_parallel": true,
319
- "self": 0.10996156098690335,
320
- "children": {
321
- "env_step": {
322
- "total": 216.61229313401464,
323
- "count": 9734,
324
- "is_parallel": true,
325
- "self": 138.77459330299052,
326
- "children": {
327
- "SubprocessEnvManager._take_step": {
328
- "total": 77.70682974300598,
329
- "count": 9735,
330
- "is_parallel": true,
331
- "self": 0.5320899129960708,
332
- "children": {
333
- "TorchPolicy.evaluate": {
334
- "total": 77.17473983000991,
335
- "count": 9734,
336
- "is_parallel": true,
337
- "self": 77.17473983000991
338
- }
339
- }
340
- },
341
- "workers": {
342
- "total": 0.11138473701794283,
343
- "count": 9734,
344
- "is_parallel": true,
345
- "self": 0.0,
346
- "children": {
347
- "worker_root": {
348
- "total": 218.37293420703372,
349
- "count": 9734,
350
- "is_parallel": true,
351
- "self": 133.69283954506045,
352
- "children": {
353
- "run_training.setup": {
354
- "total": 0.0,
355
- "count": 0,
356
- "is_parallel": true,
357
- "self": 0.0,
358
- "children": {
359
- "steps_from_proto": {
360
- "total": 0.0012318619997131464,
361
- "count": 1,
362
- "is_parallel": true,
363
- "self": 0.0003433719984968775,
364
- "children": {
365
- "_process_rank_one_or_two_observation": {
366
- "total": 0.0008884900012162689,
367
- "count": 10,
368
- "is_parallel": true,
369
- "self": 0.0008884900012162689
370
- }
371
- }
372
- },
373
- "UnityEnvironment.step": {
374
- "total": 0.020183925999845087,
375
- "count": 1,
376
- "is_parallel": true,
377
- "self": 0.00022471199963547406,
378
- "children": {
379
- "UnityEnvironment._generate_step_input": {
380
- "total": 0.00030967300017437083,
381
- "count": 1,
382
- "is_parallel": true,
383
- "self": 0.00030967300017437083
384
- },
385
- "communicator.exchange": {
386
- "total": 0.018938994000109233,
387
- "count": 1,
388
- "is_parallel": true,
389
- "self": 0.018938994000109233
390
- },
391
- "steps_from_proto": {
392
- "total": 0.0007105469999260094,
393
- "count": 1,
394
- "is_parallel": true,
395
- "self": 0.00016136200065375306,
396
- "children": {
397
- "_process_rank_one_or_two_observation": {
398
- "total": 0.0005491849992722564,
399
- "count": 10,
400
- "is_parallel": true,
401
- "self": 0.0005491849992722564
402
- }
403
- }
404
- }
405
- }
406
- }
407
- }
408
- },
409
- "UnityEnvironment.step": {
410
- "total": 84.68009466197327,
411
- "count": 9733,
412
- "is_parallel": true,
413
- "self": 2.215823559902674,
414
- "children": {
415
- "UnityEnvironment._generate_step_input": {
416
- "total": 1.3374793520260937,
417
- "count": 9733,
418
- "is_parallel": true,
419
- "self": 1.3374793520260937
420
- },
421
- "communicator.exchange": {
422
- "total": 74.01790351403406,
423
- "count": 9733,
424
- "is_parallel": true,
425
- "self": 74.01790351403406
426
- },
427
- "steps_from_proto": {
428
- "total": 7.1088882360104435,
429
- "count": 9732,
430
- "is_parallel": true,
431
- "self": 1.4775886421157338,
432
- "children": {
433
- "_process_rank_one_or_two_observation": {
434
- "total": 5.63129959389471,
435
- "count": 97320,
436
- "is_parallel": true,
437
- "self": 5.63129959389471
438
- }
439
- }
440
- }
441
- }
442
- }
443
- }
444
- }
445
- }
446
- },
447
- "steps_from_proto": {
448
- "total": 0.0013589640002464876,
449
- "count": 1,
450
- "is_parallel": true,
451
- "self": 0.0003092639999522362,
452
- "children": {
453
- "_process_rank_one_or_two_observation": {
454
- "total": 0.0010497000002942514,
455
- "count": 10,
456
- "is_parallel": true,
457
- "self": 0.0010497000002942514
458
- }
459
- }
460
- },
461
- "UnityEnvironment.step": {
462
- "total": 0.018126386999938404,
463
- "count": 1,
464
- "is_parallel": true,
465
- "self": 0.00042900400012513273,
466
- "children": {
467
- "UnityEnvironment._generate_step_input": {
468
- "total": 0.0001638520002416044,
469
- "count": 1,
470
- "is_parallel": true,
471
- "self": 0.0001638520002416044
472
- },
473
- "communicator.exchange": {
474
- "total": 0.016601101999640377,
475
- "count": 1,
476
- "is_parallel": true,
477
- "self": 0.016601101999640377
478
- },
479
- "steps_from_proto": {
480
- "total": 0.0009324289999312896,
481
- "count": 1,
482
- "is_parallel": true,
483
- "self": 0.00022863200001665973,
484
- "children": {
485
- "_process_rank_one_or_two_observation": {
486
- "total": 0.0007037969999146299,
487
- "count": 10,
488
- "is_parallel": true,
489
- "self": 0.0007037969999146299
490
- }
491
- }
492
- }
493
- }
494
- }
495
- }
496
  }
497
  }
498
  }
@@ -507,9 +309,9 @@
507
  }
508
  },
509
  "trainer_threads": {
510
- "total": 0.0001561809999657271,
511
  "count": 1,
512
- "self": 0.0001561809999657271,
513
  "children": {
514
  "thread_root": {
515
  "total": 0.0,
@@ -518,36 +320,36 @@
518
  "self": 0.0,
519
  "children": {
520
  "trainer_advance": {
521
- "total": 417.11448671301605,
522
- "count": 557850,
523
  "is_parallel": true,
524
- "self": 8.310786488148551,
525
  "children": {
526
  "process_trajectory": {
527
- "total": 287.0709264548673,
528
- "count": 557850,
529
  "is_parallel": true,
530
- "self": 286.5779193638673,
531
  "children": {
532
  "RLTrainer._checkpoint": {
533
- "total": 0.4930070909999813,
534
- "count": 4,
535
  "is_parallel": true,
536
- "self": 0.4930070909999813
537
  }
538
  }
539
  },
540
  "_update_policy": {
541
- "total": 121.73277377000022,
542
- "count": 19,
543
  "is_parallel": true,
544
- "self": 43.288195625979824,
545
  "children": {
546
  "TorchPPOOptimizer.update": {
547
- "total": 78.4445781440204,
548
- "count": 3860,
549
  "is_parallel": true,
550
- "self": 78.4445781440204
551
  }
552
  }
553
  }
@@ -558,14 +360,14 @@
558
  }
559
  },
560
  "TrainerController._save_models": {
561
- "total": 0.06739302799996949,
562
  "count": 1,
563
- "self": 0.0008943679999902088,
564
  "children": {
565
  "RLTrainer._checkpoint": {
566
- "total": 0.06649865999997928,
567
  "count": 1,
568
- "self": 0.06649865999997928
569
  }
570
  }
571
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0899980068206787,
6
+ "min": 1.0899980068206787,
7
+ "max": 2.0142664909362793,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 10515.2109375,
12
+ "min": 10515.2109375,
13
+ "max": 20672.41796875,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499941.0,
18
+ "min": 209989.0,
19
+ "max": 499941.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499941.0,
24
+ "min": 209989.0,
25
+ "max": 499941.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 2.5099332332611084,
30
+ "min": 1.5659252405166626,
31
+ "max": 2.5099332332611084,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 512.0263671875,
36
+ "min": 302.22357177734375,
37
+ "max": 512.0263671875,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
+ "min": 199.0,
43
  "max": 199.0,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 10945.0,
48
+ "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.163636363636364,
54
+ "min": 16.0,
55
+ "max": 25.163636363636364,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 1384.0,
60
+ "min": 704.0,
61
+ "max": 1384.0,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.163636363636364,
66
+ "min": 16.0,
67
+ "max": 25.163636363636364,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 1384.0,
72
+ "min": 704.0,
73
+ "max": 1384.0,
74
+ "count": 30
75
  },
76
  "SnowballTarget.IsTraining.mean": {
77
  "value": 1.0,
78
  "min": 1.0,
79
  "max": 1.0,
80
+ "count": 30
81
  },
82
  "SnowballTarget.IsTraining.sum": {
83
  "value": 1.0,
84
  "min": 1.0,
85
  "max": 1.0,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Losses.PolicyLoss.mean": {
89
+ "value": 0.05126684903225396,
90
+ "min": 0.04584989431561553,
91
+ "max": 0.05524927940336056,
92
+ "count": 28
93
  },
94
  "SnowballTarget.Losses.PolicyLoss.sum": {
95
+ "value": 0.05126684903225396,
96
+ "min": 0.04584989431561553,
97
+ "max": 0.05524927940336056,
98
+ "count": 28
99
  },
100
  "SnowballTarget.Losses.ValueLoss.mean": {
101
+ "value": 0.13929917298257352,
102
+ "min": 0.1342815386876464,
103
+ "max": 0.16858418747782708,
104
+ "count": 28
105
  },
106
  "SnowballTarget.Losses.ValueLoss.sum": {
107
+ "value": 0.13929917298257352,
108
+ "min": 0.1342815386876464,
109
+ "max": 0.16858418747782708,
110
+ "count": 28
111
  },
112
  "SnowballTarget.Policy.LearningRate.mean": {
113
+ "value": 1.4598985401999997e-06,
114
+ "min": 1.4598985401999997e-06,
115
+ "max": 5.7797442202600006e-05,
116
+ "count": 28
117
  },
118
  "SnowballTarget.Policy.LearningRate.sum": {
119
+ "value": 1.4598985401999997e-06,
120
+ "min": 1.4598985401999997e-06,
121
+ "max": 5.7797442202600006e-05,
122
+ "count": 28
123
  },
124
  "SnowballTarget.Policy.Epsilon.mean": {
125
+ "value": 0.10145980000000002,
126
+ "min": 0.10145980000000002,
127
+ "max": 0.1577974,
128
+ "count": 28
129
  },
130
  "SnowballTarget.Policy.Epsilon.sum": {
131
+ "value": 0.10145980000000002,
132
+ "min": 0.10145980000000002,
133
+ "max": 0.1577974,
134
+ "count": 28
135
  },
136
  "SnowballTarget.Policy.Beta.mean": {
137
+ "value": 8.284402e-05,
138
+ "min": 8.284402e-05,
139
+ "max": 0.0028940902600000005,
140
+ "count": 28
141
  },
142
  "SnowballTarget.Policy.Beta.sum": {
143
+ "value": 8.284402e-05,
144
+ "min": 8.284402e-05,
145
+ "max": 0.0028940902600000005,
146
+ "count": 28
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1678766969",
152
  "python_version": "3.9.5 (default, Nov 23 2021, 15:27:38) \n[GCC 9.3.0]",
153
+ "command_line_arguments": "/home/sebastian/.virtualenvs/deep_rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
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": "1.13.1+cu117",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1678767579"
160
  },
161
+ "total": 610.5692535539993,
162
  "count": 1,
163
+ "self": 0.21859918699919945,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.009277031000237912,
167
  "count": 1,
168
+ "self": 0.009277031000237912
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 610.3413773359998,
172
  "count": 1,
173
+ "self": 0.6872342400256457,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.035470527000143,
177
  "count": 1,
178
+ "self": 2.035470527000143
179
  },
180
  "TrainerController.advance": {
181
+ "total": 607.531585887974,
182
+ "count": 27275,
183
+ "self": 0.3013475419538736,
184
  "children": {
185
  "env_step": {
186
+ "total": 607.2302383460201,
187
+ "count": 27275,
188
+ "self": 388.60798734409855,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 218.3174869959539,
192
+ "count": 27275,
193
+ "self": 1.5738390700316813,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 216.74364792592223,
197
+ "count": 27275,
198
+ "self": 216.74364792592223
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.30476400596762687,
204
+ "count": 27275,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 609.2075701940394,
209
+ "count": 27275,
210
  "is_parallel": true,
211
+ "self": 368.6318694520169,
212
  "children": {
213
  "run_training.setup": {
214
+ "total": 0.0,
215
+ "count": 0,
216
  "is_parallel": true,
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0013228629995865049,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0004001460001745727,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0009227169994119322,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0009227169994119322
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.01990859299985459,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0002577320001364569,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0002522830000089016,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0002522830000089016
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.01867592100006732,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.01867592100006732
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.000722656999641913,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0001533209988338058,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005693360008081072,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0005693360008081072
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 240.5757007420225,
271
+ "count": 27274,
272
  "is_parallel": true,
273
+ "self": 6.1114115691034385,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 3.7374371960195276,
277
+ "count": 27274,
278
  "is_parallel": true,
279
+ "self": 3.7374371960195276
280
  },
281
  "communicator.exchange": {
282
+ "total": 212.46255429088797,
283
+ "count": 27274,
284
  "is_parallel": true,
285
+ "self": 212.46255429088797
286
  },
287
  "steps_from_proto": {
288
+ "total": 18.26429768601156,
289
+ "count": 27274,
290
  "is_parallel": true,
291
+ "self": 4.015080995896824,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 14.249216690114736,
295
+ "count": 272740,
296
  "is_parallel": true,
297
+ "self": 14.249216690114736
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 5.861099998583086e-05,
313
  "count": 1,
314
+ "self": 5.861099998583086e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 603.7645514752248,
324
+ "count": 810009,
325
  "is_parallel": true,
326
+ "self": 11.483299925617757,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 415.5946609176117,
330
+ "count": 810009,
331
  "is_parallel": true,
332
+ "self": 414.73243225061196,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.8622286669997266,
336
+ "count": 6,
337
  "is_parallel": true,
338
+ "self": 0.8622286669997266
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 176.6865906319954,
344
+ "count": 28,
345
  "is_parallel": true,
346
+ "self": 61.52528520197757,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 115.16130543001782,
350
+ "count": 5670,
351
  "is_parallel": true,
352
+ "self": 115.16130543001782
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.08702807000008761,
364
  "count": 1,
365
+ "self": 0.0019151289998262655,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.08511294100026134,
369
  "count": 1,
370
+ "self": 0.08511294100026134
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
4
- {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 7.0,
8
- "creation_time": 1678764711.003355,
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": 11.0,
17
- "creation_time": 1678764814.0128064,
18
- "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
- ]
21
- },
22
  {
23
  "steps": 149949,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149949.onnx",
@@ -45,15 +27,78 @@
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200101.pt"
47
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200101,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 16.181818181818183,
54
- "creation_time": 1678765032.6296148,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200101.pt"
57
  ]
58
  }
59
  },
 
1
  {
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 149949,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149949.onnx",
 
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200101.pt"
29
  ]
30
+ },
31
+ {
32
+ "steps": 249973,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249973.onnx",
34
+ "reward": 18.484848484848484,
35
+ "creation_time": 1678767070.2874954,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249973.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 299997,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299997.onnx",
43
+ "reward": 20.636363636363637,
44
+ "creation_time": 1678767173.11691,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299997.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349957,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349957.onnx",
52
+ "reward": 22.681818181818183,
53
+ "creation_time": 1678767275.7172818,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349957.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399957,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399957.onnx",
61
+ "reward": null,
62
+ "creation_time": 1678767378.7573996,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399957.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449981,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449981.onnx",
70
+ "reward": 24.65909090909091,
71
+ "creation_time": 1678767476.494734,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449981.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499941,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499941.onnx",
79
+ "reward": 25.181818181818183,
80
+ "creation_time": 1678767579.5173233,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499941.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500005,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500005.onnx",
88
+ "reward": 25.181818181818183,
89
+ "creation_time": 1678767579.620843,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500005.pt"
92
+ ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500005,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 25.181818181818183,
99
+ "creation_time": 1678767579.620843,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500005.pt"
102
  ]
103
  }
104
  },