Hugging Face's logo

vicsonsam
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
vicsonsam commited on
Commit
b89b3e6
·
verified ·
1 Parent(s): eb309f1

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +3 -0
  3. SnowballTarget/SnowballTarget-149984.pt +3 -0
  4. SnowballTarget/SnowballTarget-199984.onnx +3 -0
  5. SnowballTarget/SnowballTarget-199984.pt +3 -0
  6. SnowballTarget/SnowballTarget-200112.onnx +3 -0
  7. SnowballTarget/SnowballTarget-200112.pt +3 -0
  8. SnowballTarget/SnowballTarget-49936.onnx +3 -0
  9. SnowballTarget/SnowballTarget-49936.pt +3 -0
  10. SnowballTarget/SnowballTarget-99960.onnx +3 -0
  11. SnowballTarget/SnowballTarget-99960.pt +3 -0
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1784330102.dbe4b120f696.20739.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +14 -17
  17. run_logs/timers.json +168 -161
  18. run_logs/training_status.json +49 -4
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0093032884dc73dea77dc85fb377110e03ec2bdbd4e8849720dca4024f6f6ceb
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9978f21ab2fe94514e15f2db3f6f9bc40bbf7fff18ad44fdffd8e9a88a0c634d
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c0fff694c02abe409361253e33795e847521812b83422a514f57cadf7ccdcd
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f009d0c0d15839fd5fc77153267b2d2e31dac373e5f675d4c0f0e6c2eca649d8
3
+ size 3849902
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9978f21ab2fe94514e15f2db3f6f9bc40bbf7fff18ad44fdffd8e9a88a0c634d
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b97b41e60d275fe3a69111240984c25a6db3c5203d5d25634c449dd999210b7
3
+ size 3849902
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9978f21ab2fe94514e15f2db3f6f9bc40bbf7fff18ad44fdffd8e9a88a0c634d
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26dc65851e8f820cc9211cacf7e7f702d0ab346351011d5b37197447fdb9d52
3
+ size 3849902
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02105fe5ae1a53044b10466a1548939d232cad1fa452203e913b8453926a3cc
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e216ad6d4bc7c06b99e3ca6c0778fa64346cf1469c944b9c39bd8d8ca4d03e79
3
+ size 3849827
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a5d114ccb1c04a36dccc62f5c679593df52c242e95d42efd2488b4ef31a91f
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5853969e3ad316828c21187edd41cb43d7895f6f19fd71acbb753b4a06a29ec
3
+ size 3849827
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3af82fb98cf623cc278d6b005969a688faa4c7d7b4a0cf4bd4f3f30ef0518bb8
3
  size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e31db464bae403becebf38c8bd52a1c20d371a127218681c02ae88c3fc13049
3
  size 3849077
SnowballTarget/events.out.tfevents.1784330102.dbe4b120f696.20739.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2473fbb447ea196a6695729235af2e393bbd9a585630f375cb1f20f4a161ac19
3
+ size 22312
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -69,7 +69,7 @@ checkpoint_settings:
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
- resume: false
73
  force: false
74
  train_model: false
75
  inference: false
 
69
  run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
+ resume: true
73
  force: false
74
  train_model: false
75
  inference: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.205 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.810464 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]: 359 frames, [16.0 KB-32.0 KB]: 6 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 37
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]: 366 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 5.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 366 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]: 324 frames, [64.0 KB-128.0 KB]: 42 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.0 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 366 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]: 366 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]: 365 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]: 366 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]: 366 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 0.081 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: 0.827229 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]: 5013 frames, [16.0 KB-32.0 KB]: 84 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 34
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]: 5098 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.0 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5098 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.3 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]: 4871 frames, [64.0 KB-128.0 KB]: 227 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5098 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]: 5098 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]: 5097 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]: 5098 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]: 5098 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 2.865175485610962,
6
- "min": 2.865175485610962,
7
- "max": 2.865175485610962,
8
- "count": 1
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 29247.7109375,
12
- "min": 29247.7109375,
13
- "max": 29247.7109375,
14
- "count": 1
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 9952.0,
18
- "min": 9952.0,
19
- "max": 9952.0,
20
- "count": 1
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 9952.0,
24
- "min": 9952.0,
25
- "max": 9952.0,
26
- "count": 1
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 0.3625098168849945,
30
- "min": 0.3625098168849945,
31
- "max": 0.3625098168849945,
32
- "count": 1
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 70.326904296875,
36
- "min": 70.326904296875,
37
- "max": 70.326904296875,
38
- "count": 1
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06757534932231625,
42
- "min": 0.06757534932231625,
43
- "max": 0.06757534932231625,
44
- "count": 1
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.270301397289265,
48
- "min": 0.270301397289265,
49
- "max": 0.270301397289265,
50
- "count": 1
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.11607839194281648,
54
- "min": 0.11607839194281648,
55
- "max": 0.11607839194281648,
56
- "count": 1
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.4643135677712659,
60
- "min": 0.4643135677712659,
61
- "max": 0.4643135677712659,
62
- "count": 1
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 0.000291882002706,
66
- "min": 0.000291882002706,
67
- "max": 0.000291882002706,
68
- "count": 1
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 0.001167528010824,
72
- "min": 0.001167528010824,
73
- "max": 0.001167528010824,
74
- "count": 1
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.19729400000000002,
78
- "min": 0.19729400000000002,
79
- "max": 0.19729400000000002,
80
- "count": 1
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.7891760000000001,
84
- "min": 0.7891760000000001,
85
- "max": 0.7891760000000001,
86
- "count": 1
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0048649706,
90
- "min": 0.0048649706,
91
- "max": 0.0048649706,
92
- "count": 1
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0194598824,
96
- "min": 0.0194598824,
97
- "max": 0.0194598824,
98
- "count": 1
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 1
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
- "min": 8756.0,
109
- "max": 8756.0,
110
- "count": 1
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 3.2954545454545454,
114
- "min": 3.2954545454545454,
115
- "max": 3.2954545454545454,
116
- "count": 1
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 145.0,
120
- "min": 145.0,
121
- "max": 145.0,
122
- "count": 1
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 3.2954545454545454,
126
- "min": 3.2954545454545454,
127
- "max": 3.2954545454545454,
128
- "count": 1
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 145.0,
132
- "min": 145.0,
133
- "max": 145.0,
134
- "count": 1
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 1
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 1
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1784329793",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1784329831"
160
  },
161
- "total": 38.51977383300027,
162
  "count": 1,
163
- "self": 0.21772640100061835,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02759821799963902,
167
  "count": 1,
168
- "self": 0.02759821799963902
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 38.274449214000015,
172
  "count": 1,
173
- "self": 0.032392797998454625,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.4226133970000774,
177
  "count": 1,
178
- "self": 3.4226133970000774
179
  },
180
  "TrainerController.advance": {
181
- "total": 34.5959766290016,
182
- "count": 1218,
183
- "self": 0.032454106997192866,
184
  "children": {
185
  "env_step": {
186
- "total": 26.208069185000113,
187
- "count": 1218,
188
- "self": 20.66967926399775,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 5.520639402994675,
192
- "count": 1218,
193
- "self": 0.10204994700143288,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 5.418589455993242,
197
- "count": 1218,
198
- "self": 5.418589455993242
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.017750518007687788,
204
- "count": 1217,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 37.95430914998815,
209
- "count": 1217,
210
  "is_parallel": true,
211
- "self": 19.915574421991096,
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": 0.004245446999902924,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0028529650007840246,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0013924819991188997,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0013924819991188997
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.04420377599990388,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006577829999514506,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.000422798999807128,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.000422798999807128
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04098152699998536,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04098152699998536
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021416670001599414,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0005086310006845451,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016330359994753962,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016330359994753962
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 18.038734727997053,
271
- "count": 1216,
272
  "is_parallel": true,
273
- "self": 0.741069802003949,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 0.41046097499884127,
277
- "count": 1216,
278
  "is_parallel": true,
279
- "self": 0.41046097499884127
280
  },
281
  "communicator.exchange": {
282
- "total": 13.972796490999826,
283
- "count": 1216,
284
  "is_parallel": true,
285
- "self": 13.972796490999826
286
  },
287
  "steps_from_proto": {
288
- "total": 2.914407459994436,
289
- "count": 1216,
290
  "is_parallel": true,
291
- "self": 0.5098467749812698,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 2.404560685013166,
295
- "count": 12160,
296
  "is_parallel": true,
297
- "self": 2.404560685013166
298
  }
299
  }
300
  }
@@ -307,24 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 8.355453337004292,
311
- "count": 1217,
312
- "self": 0.03958448399498593,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 1.8974690750087575,
316
- "count": 1217,
317
- "self": 1.8974690750087575
 
 
 
 
 
 
 
318
  },
319
  "_update_policy": {
320
- "total": 6.418399778000548,
321
- "count": 6,
322
- "self": 2.557056286000261,
323
  "children": {
324
  "TorchPPOOptimizer.update": {
325
- "total": 3.8613434920002874,
326
- "count": 303,
327
- "self": 3.8613434920002874
328
  }
329
  }
330
  }
@@ -333,19 +340,19 @@
333
  }
334
  },
335
  "trainer_threads": {
336
- "total": 1.4830002328380942e-06,
337
  "count": 1,
338
- "self": 1.4830002328380942e-06
339
  },
340
  "TrainerController._save_models": {
341
- "total": 0.22346490699965216,
342
  "count": 1,
343
- "self": 0.0008174459994734207,
344
  "children": {
345
  "RLTrainer._checkpoint": {
346
- "total": 0.22264746100017874,
347
  "count": 1,
348
- "self": 0.22264746100017874
349
  }
350
  }
351
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.87007075548172,
6
+ "min": 0.8571820855140686,
7
+ "max": 2.665627956390381,
8
+ "count": 19
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8269.15234375,
12
+ "min": 8269.15234375,
13
+ "max": 23946.328125,
14
+ "count": 19
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
+ "min": 19992.0,
19
+ "max": 199984.0,
20
+ "count": 19
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
+ "min": 19992.0,
25
+ "max": 199984.0,
26
+ "count": 19
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.028005599975586,
30
+ "min": 1.848665475845337,
31
+ "max": 13.028005599975586,
32
+ "count": 19
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2540.461181640625,
36
+ "min": 249.56983947753906,
37
+ "max": 2646.088623046875,
38
+ "count": 19
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.07174146862006656,
42
+ "min": 0.06283611220495752,
43
+ "max": 0.07404320597547043,
44
+ "count": 19
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2869658744802662,
48
+ "min": 0.20686593932061093,
49
+ "max": 0.36268202800263183,
50
+ "count": 19
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.2055351081139901,
54
+ "min": 0.1978417685803245,
55
+ "max": 0.2898271525753479,
56
+ "count": 19
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.8221404324559604,
60
+ "min": 0.7168980026617646,
61
+ "max": 1.3873297951969448,
62
+ "count": 19
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 8.082097306000005e-06,
66
+ "min": 8.082097306000005e-06,
67
+ "max": 0.000273732008756,
68
+ "count": 19
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.232838922400002e-05,
72
+ "min": 3.232838922400002e-05,
73
+ "max": 0.00123666008778,
74
+ "count": 19
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10269400000000001,
78
+ "min": 0.10269400000000001,
79
+ "max": 0.191244,
80
+ "count": 19
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.41077600000000003,
84
+ "min": 0.41077600000000003,
85
+ "max": 0.91222,
86
+ "count": 19
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.0001444306000000001,
90
+ "min": 0.0001444306000000001,
91
+ "max": 0.0045630756,
92
+ "count": 19
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0005777224000000004,
96
+ "min": 0.0005777224000000004,
97
+ "max": 0.020619778000000002,
98
+ "count": 19
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 19
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
  "value": 8756.0,
108
+ "min": 6567.0,
109
+ "max": 10945.0,
110
+ "count": 19
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.40909090909091,
114
+ "min": 7.424242424242424,
115
+ "max": 25.795454545454547,
116
+ "count": 19
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1118.0,
120
+ "min": 245.0,
121
+ "max": 1418.0,
122
+ "count": 19
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.40909090909091,
126
+ "min": 7.424242424242424,
127
+ "max": 25.795454545454547,
128
+ "count": 19
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1118.0,
132
+ "min": 245.0,
133
+ "max": 1418.0,
134
+ "count": 19
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 19
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 19
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1784330101",
152
  "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1784330564"
160
  },
161
+ "total": 463.261596154,
162
  "count": 1,
163
+ "self": 0.43388247700022475,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.025127798000085022,
167
  "count": 1,
168
+ "self": 0.025127798000085022
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 462.8025858789997,
172
  "count": 1,
173
+ "self": 0.43135089100542245,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.0722338129999116,
177
  "count": 1,
178
+ "self": 2.0722338129999116
179
  },
180
  "TrainerController.advance": {
181
+ "total": 460.2165094319944,
182
+ "count": 16992,
183
+ "self": 0.43877945595932033,
184
  "children": {
185
  "env_step": {
186
+ "total": 342.1979538540031,
187
+ "count": 16992,
188
+ "self": 267.7088001920565,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 74.21992059490958,
192
+ "count": 16992,
193
+ "self": 1.3496146918960221,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 72.87030590301356,
197
+ "count": 16992,
198
+ "self": 72.87030590301356
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2692330670370211,
204
+ "count": 16992,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 460.8201482589843,
209
+ "count": 16992,
210
  "is_parallel": true,
211
+ "self": 226.67615600897443,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0024085670002023107,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0007847170004424697,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001623849999759841,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001623849999759841
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.041948340000089956,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006335369998851093,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004519519998211763,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004519519998211763
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03883406900013142,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03883406900013142
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020287820002522494,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00037473500105988933,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.00165404699919236,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.00165404699919236
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 234.1439922500099,
271
+ "count": 16991,
272
  "is_parallel": true,
273
+ "self": 10.35009592603592,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.613845507002679,
277
+ "count": 16991,
278
  "is_parallel": true,
279
+ "self": 5.613845507002679
280
  },
281
  "communicator.exchange": {
282
+ "total": 180.1272439339955,
283
+ "count": 16991,
284
  "is_parallel": true,
285
+ "self": 180.1272439339955
286
  },
287
  "steps_from_proto": {
288
+ "total": 38.0528068829758,
289
+ "count": 16991,
290
  "is_parallel": true,
291
+ "self": 6.839617024669678,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 31.213189858306123,
295
+ "count": 169910,
296
  "is_parallel": true,
297
+ "self": 31.213189858306123
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 117.57977612203194,
311
+ "count": 16992,
312
+ "self": 0.5312661341417879,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 24.465700950893734,
316
+ "count": 16992,
317
+ "self": 24.03762795489456,
318
+ "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 0.42807299599917314,
321
+ "count": 4,
322
+ "self": 0.42807299599917314
323
+ }
324
+ }
325
  },
326
  "_update_policy": {
327
+ "total": 92.58280903699642,
328
+ "count": 84,
329
+ "self": 37.12785239201821,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 55.45495664497821,
333
+ "count": 4281,
334
+ "self": 55.45495664497821
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.1060001270379871e-06,
344
  "count": 1,
345
+ "self": 1.1060001270379871e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08249063699986436,
349
  "count": 1,
350
+ "self": 0.000953740000113612,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08153689699975075,
354
  "count": 1,
355
+ "self": 0.08153689699975075
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -9,15 +9,60 @@
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-13200.pt"
11
  ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  }
13
  ],
14
  "final_checkpoint": {
15
- "steps": 13200,
16
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
17
- "reward": 6.090909090909091,
18
- "creation_time": 1784329831.5940578,
19
  "auxillary_file_paths": [
20
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-13200.pt"
21
  ]
22
  }
23
  },
 
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-13200.pt"
11
  ]
12
+ },
13
+ {
14
+ "steps": 49936,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
16
+ "reward": 17.545454545454547,
17
+ "creation_time": 1784330193.568825,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 99960,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
25
+ "reward": 24.727272727272727,
26
+ "creation_time": 1784330315.7322423,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 149984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
34
+ "reward": 25.363636363636363,
35
+ "creation_time": 1784330441.64435,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 199984,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
43
+ "reward": 24.818181818181817,
44
+ "creation_time": 1784330564.3070548,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 200112,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
52
+ "reward": 24.818181818181817,
53
+ "creation_time": 1784330564.400308,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
56
+ ]
57
  }
58
  ],
59
  "final_checkpoint": {
60
+ "steps": 200112,
61
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
62
+ "reward": 24.818181818181817,
63
+ "creation_time": 1784330564.400308,
64
  "auxillary_file_paths": [
65
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
66
  ]
67
  }
68
  },