xenjin450 commited on
Commit
3686dfb
·
verified ·
1 Parent(s): bab2d69

First Push

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b6b14d913bf1e960102b05e9bd571bb5497370286c413ad4d31f24d2dde58b4
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba36e777d5bd4ad44c8c47254c42c798ce75ca3ac9be588978bff97f043781e
3
  size 2867524
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bd50844df617ded0127cb2adbfe4e7410615eef4a143ebd27b6d0a2cfbdbeca
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3dd4ddb6c472fc69b3e6993dd975b0d60002586d06d353739137e8994d321df
3
  size 2867524
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7786c33bd6395cb90224e3f2252ead95175deab831527f2de41f53b8ef45fb
3
  size 8602051
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dde6fa5637b4687a830db62b1269e2ec48b920f7151182db24831fa872fbf5
3
  size 8602051
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b6b14d913bf1e960102b05e9bd571bb5497370286c413ad4d31f24d2dde58b4
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba36e777d5bd4ad44c8c47254c42c798ce75ca3ac9be588978bff97f043781e
3
  size 2867524
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87f937f9b81222cc7c89cd9241a30dd95e6c9cde0f3151cd3c60c545a3e34a77
3
  size 8602051
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c646be6cfaa197fdfa4ad52e195debbde3114867213876439943d1e01765d0a
3
  size 8602051
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b6b14d913bf1e960102b05e9bd571bb5497370286c413ad4d31f24d2dde58b4
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba36e777d5bd4ad44c8c47254c42c798ce75ca3ac9be588978bff97f043781e
3
  size 2867524
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e6b9cf487035a53140bf51bfb8d99907edfd4ef1c1d5bb6ca490c77467c6b1a
3
  size 8602051
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e245d753fde57345c59e202761bdbd18453720c0bc3663bb8812a04b8b7ec743
3
  size 8602051
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e04c4e97a937f7f7313ab074ef2532d68117afcf882c7505790a0ffeaf9240ef
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cbe5bceadb5985faf275c35e18e8a7b5221008dbb14a4ee987b58b759b8b10
3
  size 2867524
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541471f68df4b0c24c5c8b86ef99f9528e090961010d3536a1ac6a748cc381d3
3
  size 8601984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6401e587119f53ba2091f01f6f4dfac935adcf7f8a456c28eeb4343e3ea7f659
3
  size 8601984
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76e04cae2c70f630b8ec70956f4db67ccb928afd1d807824467bee8074c4d822
3
  size 2867524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde983107ba9f5ae0bc056f3ef52bde092499f8e7b462888d2d7edac01fcefeb
3
  size 2867524
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0d9a36f95dd53a3301fe027639d6a8305515c8848d28cb726590b68a3279f5a
3
  size 8601984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b6df79113e429214a74a7a4190337c9165e8870ab74320b872f6c994b79b34
3
  size 8601984
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2183003596300821515724220666562428395d8c1aea3fb4314701b224402180
3
  size 8601314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e5e1e9d7ee1ee37fc2efe51988cea705d385a9b0a9a14f8a93f68f6f205f72
3
  size 8601314
SnowballTarget/events.out.tfevents.1738662695.cf106d47a9e7.27596.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aba77e079ad03c2ae3baeef5fc57115ce724749d78911a633acb98c7422aa27
3
+ size 28202
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 2048, "learning_rate": 0.0004, "beta": 0.005, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 5, "shared_critic": true, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "resnet", "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTargetRLXenjin450", "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": 512, "buffer_size": 2048, "learning_rate": 0.0004, "beta": 0.005, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 5, "shared_critic": true, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "resnet", "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTargetXenjin450", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTargetRLXenjin450
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTargetXenjin450
70
  initialize_from: null
71
  load_model: false
72
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.147 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: 1.076136 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]: 5371 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]: 5463 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]: 5463 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.4 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]: 5082 frames, [64.0 KB-128.0 KB]: 381 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]: 5463 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]: 5463 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]: 5462 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]: 5463 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]: 5463 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 0.195 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: 2.455169 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]: 5370 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 45
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]: 5462 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.7 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.8 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3911 frames, [64.0 KB-128.0 KB]: 1551 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 67.6 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.7426327466964722,
6
- "min": 0.731351375579834,
7
- "max": 2.87078595161438,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 7115.1640625,
12
- "min": 7115.1640625,
13
- "max": 29494.455078125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.157102584838867,
30
- "min": 0.40423882007598877,
31
- "max": 13.203481674194336,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2565.635009765625,
36
- "min": 78.42233276367188,
37
- "max": 2693.51025390625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.03378662246068416,
54
- "min": 0.024719062141757602,
55
- "max": 0.03549714893844794,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.13514648984273664,
60
- "min": 0.10262200149154523,
61
- "max": 0.17748574469223968,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20805656611919401,
66
- "min": 0.13371476717293262,
67
- "max": 0.30642091631889345,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8322262644767761,
72
- "min": 0.5348590686917305,
73
- "max": 1.4480631172657012,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -82,7 +82,7 @@
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
  "value": 4.310438922400004e-05,
84
  "min": 4.310438922400004e-05,
85
- "max": 0.0018470080382480003,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -94,7 +94,7 @@
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
  "value": 0.421552,
96
  "min": 0.421552,
97
- "max": 1.423504,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
@@ -106,31 +106,31 @@
106
  "SnowballTarget.Policy.Beta.sum": {
107
  "value": 0.0005777224000000006,
108
  "min": 0.0005777224000000006,
109
- "max": 0.0230914248,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.0,
114
- "min": 3.409090909090909,
115
- "max": 26.113636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1144.0,
120
- "min": 150.0,
121
- "max": 1424.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.0,
126
- "min": 3.409090909090909,
127
- "max": 26.113636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1144.0,
132
- "min": 150.0,
133
- "max": 1424.0,
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": "1738656550",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowBallTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetRLXenjin450 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1738657315"
160
  },
161
- "total": 765.3132163070001,
162
  "count": 1,
163
- "self": 0.5930619870000555,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.03710776100001567,
167
  "count": 1,
168
- "self": 0.03710776100001567
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 764.683046559,
172
  "count": 1,
173
- "self": 0.949189137989606,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.585462923000023,
177
  "count": 1,
178
- "self": 3.585462923000023
179
  },
180
  "TrainerController.advance": {
181
- "total": 760.0062615160103,
182
- "count": 18208,
183
- "self": 0.42497787501986295,
184
  "children": {
185
  "env_step": {
186
- "total": 759.5812836409905,
187
- "count": 18208,
188
- "self": 602.27683737699,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 156.8676528189999,
192
- "count": 18208,
193
- "self": 2.4283309699890196,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 154.43932184901087,
197
- "count": 18208,
198
- "self": 154.43932184901087
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.43679344500060324,
204
- "count": 18208,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 762.6161606029825,
209
- "count": 18208,
210
  "is_parallel": true,
211
- "self": 438.6304640459622,
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": 0.007090471999958936,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004857103999938772,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002233368000020164,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002233368000020164
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04775891999997839,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0008827899999914735,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00045350200002758356,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00045350200002758356
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04406474100005653,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04406474100005653
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002357886999902803,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004984689996945235,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018594180002082794,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018594180002082794
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 323.98569655702033,
271
- "count": 18207,
272
  "is_parallel": true,
273
- "self": 13.650050263036519,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 7.71489115998736,
277
- "count": 18207,
278
  "is_parallel": true,
279
- "self": 7.71489115998736
280
  },
281
  "communicator.exchange": {
282
- "total": 259.3493254720022,
283
- "count": 18207,
284
  "is_parallel": true,
285
- "self": 259.3493254720022
286
  },
287
  "steps_from_proto": {
288
- "total": 43.27142966199426,
289
- "count": 18207,
290
  "is_parallel": true,
291
- "self": 8.577398599008802,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 34.69403106298546,
295
- "count": 182070,
296
  "is_parallel": true,
297
- "self": 34.69403106298546
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.000221620000047551,
313
  "count": 1,
314
- "self": 0.000221620000047551,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 753.5991227619644,
324
- "count": 760786,
325
  "is_parallel": true,
326
- "self": 17.114075343134118,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 338.4741784408303,
330
- "count": 760786,
331
  "is_parallel": true,
332
- "self": 337.1586647528302,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.3155136880001237,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.3155136880001237
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 398.01086897799996,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 97.17286447700337,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 300.8380045009966,
350
  "count": 1800,
351
  "is_parallel": true,
352
- "self": 300.8380045009966
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.14191136199997345,
364
  "count": 1,
365
- "self": 0.007087764000061725,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13482359799991173,
369
  "count": 1,
370
- "self": 0.13482359799991173
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6928920745849609,
6
+ "min": 0.6928920745849609,
7
+ "max": 2.878577470779419,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6646.220703125,
12
+ "min": 6646.220703125,
13
+ "max": 29574.50390625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 11.981770515441895,
30
+ "min": 0.29059553146362305,
31
+ "max": 11.981770515441895,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2336.4453125,
36
+ "min": 56.37553405761719,
37
+ "max": 2440.07568359375,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.0296454241455649,
54
+ "min": 0.028084085073787724,
55
+ "max": 0.037452506452100354,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.1185816965822596,
60
+ "min": 0.1185816965822596,
61
+ "max": 0.18726253226050177,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.19328838884830474,
66
+ "min": 0.10373825123533606,
67
+ "max": 0.290578506141901,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.773153555393219,
72
+ "min": 0.41495300494134424,
73
+ "max": 1.3859055444598198,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
  "value": 4.310438922400004e-05,
84
  "min": 4.310438922400004e-05,
85
+ "max": 0.0018468800382800002,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
 
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
  "value": 0.421552,
96
  "min": 0.421552,
97
+ "max": 1.42344,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
 
106
  "SnowballTarget.Policy.Beta.sum": {
107
  "value": 0.0005777224000000006,
108
  "min": 0.0005777224000000006,
109
+ "max": 0.023089828,
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 23.681818181818183,
114
+ "min": 2.6818181818181817,
115
+ "max": 23.70909090909091,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1042.0,
120
+ "min": 118.0,
121
+ "max": 1304.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 23.681818181818183,
126
+ "min": 2.6818181818181817,
127
+ "max": 23.70909090909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1042.0,
132
+ "min": 118.0,
133
+ "max": 1304.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1738662694",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetXenjin450 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1738663506"
160
  },
161
+ "total": 812.5668383210004,
162
  "count": 1,
163
+ "self": 0.6927915620008207,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03452016699975502,
167
  "count": 1,
168
+ "self": 0.03452016699975502
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 811.8395265919999,
172
  "count": 1,
173
+ "self": 1.07995954297985,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.42389432499931,
177
  "count": 1,
178
+ "self": 3.42389432499931
179
  },
180
  "TrainerController.advance": {
181
+ "total": 807.1814257440201,
182
+ "count": 18206,
183
+ "self": 0.49803600401173753,
184
  "children": {
185
  "env_step": {
186
+ "total": 806.6833897400084,
187
+ "count": 18206,
188
+ "self": 640.9386373739844,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 165.25657096709983,
192
+ "count": 18206,
193
+ "self": 2.93720667904563,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 162.3193642880542,
197
+ "count": 18206,
198
+ "self": 162.3193642880542
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4881813989240982,
204
+ "count": 18206,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 809.5793749020659,
209
+ "count": 18206,
210
  "is_parallel": true,
211
+ "self": 463.8940645060702,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.004620794999937061,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.001583236999977089,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0030375579999599722,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0030375579999599722
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.15677927999968233,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0037805080000907765,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004818150000573951,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004818150000573951
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.13114621299973805,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.13114621299973805
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.021370743999796105,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.005355924999093986,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.01601481900070212,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.01601481900070212
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 345.68531039599566,
271
+ "count": 18205,
272
  "is_parallel": true,
273
+ "self": 14.406276040003831,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.994227226001385,
277
+ "count": 18205,
278
  "is_parallel": true,
279
+ "self": 7.994227226001385
280
  },
281
  "communicator.exchange": {
282
+ "total": 278.1204304049734,
283
+ "count": 18205,
284
  "is_parallel": true,
285
+ "self": 278.1204304049734
286
  },
287
  "steps_from_proto": {
288
+ "total": 45.164376725017064,
289
+ "count": 18205,
290
  "is_parallel": true,
291
+ "self": 9.234507885953462,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 35.9298688390636,
295
+ "count": 182050,
296
  "is_parallel": true,
297
+ "self": 35.9298688390636
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00023182800032373052,
313
  "count": 1,
314
+ "self": 0.00023182800032373052,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 800.2991470469851,
324
+ "count": 828679,
325
  "is_parallel": true,
326
+ "self": 18.937228551389126,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 362.3103792215943,
330
+ "count": 828679,
331
  "is_parallel": true,
332
+ "self": 360.76179730759395,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.5485819140003514,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.5485819140003514
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 419.0515392740017,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 98.93746979500156,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 320.11406947900014,
350
  "count": 1800,
351
  "is_parallel": true,
352
+ "self": 320.11406947900014
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.1540151520002837,
364
  "count": 1,
365
+ "self": 0.004700188000242633,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14931496400004107,
369
  "count": 1,
370
+ "self": 0.14931496400004107
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 18.545454545454547,
8
- "creation_time": 1738656745.9923544,
9
  "auxillary_file_paths": [
10
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 25.181818181818183,
17
- "creation_time": 1738656933.7699564,
18
  "auxillary_file_paths": [
19
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 26.09090909090909,
26
- "creation_time": 1738657127.274378,
27
  "auxillary_file_paths": [
28
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.363636363636363,
35
- "creation_time": 1738657315.1212382,
36
  "auxillary_file_paths": [
37
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.363636363636363,
44
- "creation_time": 1738657315.280354,
45
  "auxillary_file_paths": [
46
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
- "file_path": "results/SnowballTargetRLXenjin450/SnowballTarget.onnx",
53
- "reward": 26.363636363636363,
54
- "creation_time": 1738657315.280354,
55
  "auxillary_file_paths": [
56
- "results/SnowballTargetRLXenjin450/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.636363636363637,
8
+ "creation_time": 1738662894.4801404,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 22.727272727272727,
17
+ "creation_time": 1738663097.372155,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 24.09090909090909,
26
+ "creation_time": 1738663302.5231082,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 23.90909090909091,
35
+ "creation_time": 1738663506.0177546,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 23.90909090909091,
44
+ "creation_time": 1738663506.209956,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTargetXenjin450/SnowballTarget.onnx",
53
+ "reward": 23.90909090909091,
54
+ "creation_time": 1738663506.209956,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTargetXenjin450/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },