Hugging Face's logo

adhisetiawan
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
adhisetiawan commited on
Commit
3ee64fc
•
1 Parent(s): bdbd567

change number of layers

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-149984.onnx +2 -2
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +2 -2
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +2 -2
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +2 -2
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +2 -2
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/{events.out.tfevents.1679902715.efb1629e622b.2657.0 → events.out.tfevents.1679908425.efb1629e622b.26805.0} +2 -2
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +12 -15
  17. run_logs/timers.json +111 -111
  18. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7e2c5d3bd5a7b681a7452c45a6330d1923dded42f78f3d54f109b838eadc3e5
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
+ size 910131
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb42f8d4c0886137a71f8212e60fea4e163330ba0274a45b3d1223915bd4946
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbca599c83610ecdad2c6f9d8a66442440a2840c24aa0c33b3f20cd6d9031ccd
3
+ size 910131
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00dc1534137383652074b3ef6ef78bb79f12a2215816e432b898ba4a030eac3
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f085bd423c674e2558e9c02b3e195d97608821a937c1e3c1de22c6cb01b2d7
3
+ size 5426908
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7e2c5d3bd5a7b681a7452c45a6330d1923dded42f78f3d54f109b838eadc3e5
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
+ size 910131
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db09a26a9d209ff31a03d4d95352e2a3151141ed9e0c2dc5edb43b052022a889
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ce224edaf67a70520a025f68c2be3a3c7c0a6d7ee46f38489058191817b78b
3
+ size 5426908
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7e2c5d3bd5a7b681a7452c45a6330d1923dded42f78f3d54f109b838eadc3e5
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510fffc23a002d6bc4c199621b6f673a1ed128eed7f99a2a3a4f4194a723e173
3
+ size 910131
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f160aaa60e9e1272e249e32e757a6cf4c08efb8fd6be98b9d61683dcb9417dc0
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da66ee1bddfded35b863053faaed30ae4d70826e2e4b3eafbf0e073fac71638e
3
+ size 5426908
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f95aaec83d4aa6c3a740903c7e27882f499df754a2affb5d692e2fc5c4f8827
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13eb0df36312a46fdd37125cf03bc8395537f1a17eeab36b9382829a9404a6b3
3
+ size 910131
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:964b4c29ac96e4b711da3d56aea89191ab20c7bceac794004ebced0802af55c0
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d5bf107be74b3091fcb1c34699b02b05a60f39b7a1ccb4ada03b33339c1805
3
+ size 5426908
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1818687e11dc5c49876c6421c88362ce1caff9ee0f96539e3f5ed23d8aad885
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9dbc35d4da555d203f2ee0d0c46db73d3af5f7d6a40b2729da683b7e57c003
3
+ size 910131
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc3f831cc339ee1131d2e4cd167a3d8348a7c00dad344aafbcb66b40e5cc1b7b
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37db3c05a9a0fb9f370ef6070cc91e468c84f888231660312afc032b8a2e60b
3
+ size 5426908
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f160aaa60e9e1272e249e32e757a6cf4c08efb8fd6be98b9d61683dcb9417dc0
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da66ee1bddfded35b863053faaed30ae4d70826e2e4b3eafbf0e073fac71638e
3
+ size 5426908
SnowballTarget/{events.out.tfevents.1679902715.efb1629e622b.2657.0 → events.out.tfevents.1679908425.efb1629e622b.26805.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d68530243d31cde090f9635a27f3df293140b8b3fa932b5c5977bce972389fa
3
- size 23702
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca596d92751d486ddd019de384f3d3f165ab6bda1de02a51c33eaa0e3ce28f8
3
+ size 23489
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "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": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -18,7 +18,7 @@ behaviors:
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
- num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
@@ -68,7 +68,7 @@ checkpoint_settings:
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
- force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
 
18
  network_settings:
19
  normalize: false
20
  hidden_units: 256
21
+ num_layers: 3
22
  vis_encode_type: simple
23
  memory: null
24
  goal_conditioning_type: hyper
 
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
+ force: true
72
  train_model: false
73
  inference: false
74
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(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 0.091 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: 0.666829 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]: 5369 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
@@ -169,19 +166,19 @@ 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]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
  Peak Allocated memory 6.7 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 5017 frames, [64.0 KB-128.0 KB]: 444 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
  Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 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]: 5461 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]: 5460 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]: 5461 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]: 5461 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 0.080 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: 0.649644 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]: 5374 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 42
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]: 5466 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]: 5466 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 4388 frames, [64.0 KB-128.0 KB]: 1078 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5466 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]: 5466 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]: 5465 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]: 5466 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]: 5466 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": 0.94545978307724,
6
- "min": 0.916050374507904,
7
- "max": 2.867387533187866,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9027.25,
12
- "min": 8837.1376953125,
13
- "max": 29396.45703125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.051465034484863,
30
- "min": 0.27961480617523193,
31
- "max": 13.051465034484863,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2545.03564453125,
36
- "min": 54.245269775390625,
37
- "max": 2638.4033203125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07293560138314918,
54
- "min": 0.0596467264406052,
55
- "max": 0.07503485352122773,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2917424055325967,
60
- "min": 0.2597963432598786,
61
- "max": 0.37517426760613865,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.1870236031199787,
66
- "min": 0.10796726512432774,
67
- "max": 0.2893612817806356,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7480944124799148,
72
- "min": 0.43186906049731094,
73
- "max": 1.446806408903178,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.545454545454547,
114
- "min": 2.9318181818181817,
115
- "max": 25.727272727272727,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1124.0,
120
- "min": 129.0,
121
- "max": 1415.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.545454545454547,
126
- "min": 2.9318181818181817,
127
- "max": 25.727272727272727,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1124.0,
132
- "min": 129.0,
133
- "max": 1415.0,
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": "1679902709",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
153
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1679903171"
160
  },
161
- "total": 462.34764825699983,
162
  "count": 1,
163
- "self": 0.43356318499991175,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.11549864999994952,
167
  "count": 1,
168
- "self": 0.11549864999994952
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 461.79858642199997,
172
  "count": 1,
173
- "self": 0.5018591850098346,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 10.100400470000068,
177
  "count": 1,
178
- "self": 10.100400470000068
179
  },
180
  "TrainerController.advance": {
181
- "total": 451.0666685519898,
182
- "count": 18202,
183
- "self": 0.26017733399521603,
184
  "children": {
185
  "env_step": {
186
- "total": 450.80649121799456,
187
- "count": 18202,
188
- "self": 326.2002793959772,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 124.34499847501093,
192
- "count": 18202,
193
- "self": 2.645034317017007,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 121.69996415799392,
197
- "count": 18202,
198
- "self": 121.69996415799392
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2612133470064464,
204
- "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 460.47195434199557,
209
- "count": 18202,
210
  "is_parallel": true,
211
- "self": 223.98804554998026,
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": 0.0056975500000362445,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004164137999964623,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015334120000716212,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015334120000716212
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.12132309499997973,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006008689998679984,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00043788599998606514,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00043788599998606514
244
  },
245
  "communicator.exchange": {
246
- "total": 0.11834234600007676,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.11834234600007676
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019419940000489078,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00039704700009224325,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0015449469999566645,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0015449469999566645
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 236.4839087920153,
271
- "count": 18201,
272
  "is_parallel": true,
273
- "self": 9.50358736703356,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.196618792003733,
277
- "count": 18201,
278
  "is_parallel": true,
279
- "self": 5.196618792003733
280
  },
281
  "communicator.exchange": {
282
- "total": 191.09818791898738,
283
- "count": 18201,
284
  "is_parallel": true,
285
- "self": 191.09818791898738
286
  },
287
  "steps_from_proto": {
288
- "total": 30.685514713990642,
289
- "count": 18201,
290
  "is_parallel": true,
291
- "self": 5.897759952005572,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.78775476198507,
295
- "count": 182010,
296
  "is_parallel": true,
297
- "self": 24.78775476198507
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00012075600011485221,
313
  "count": 1,
314
- "self": 0.00012075600011485221,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 447.64375773002325,
324
- "count": 395087,
325
  "is_parallel": true,
326
- "self": 9.728361957030529,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 245.96384885199188,
330
- "count": 395087,
331
  "is_parallel": true,
332
- "self": 245.08376061799197,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.8800882339999134,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.8800882339999134
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 191.95154692100084,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 73.56837819000191,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 118.38316873099893,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 118.38316873099893
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.12953745900017566,
364
  "count": 1,
365
- "self": 0.0008388180001475121,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.12869864100002815,
369
  "count": 1,
370
- "self": 0.12869864100002815
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9946820735931396,
6
+ "min": 0.9946820735931396,
7
+ "max": 2.8663761615753174,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9530.048828125,
12
+ "min": 9530.048828125,
13
+ "max": 29480.677734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.850577354431152,
30
+ "min": 0.4389503598213196,
31
+ "max": 12.850577354431152,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2505.862548828125,
36
+ "min": 85.1563720703125,
37
+ "max": 2582.72509765625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07140613051103406,
54
+ "min": 0.06089604495951505,
55
+ "max": 0.07297919158322744,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.28562452204413624,
60
+ "min": 0.25895955315568514,
61
+ "max": 0.3648959579161372,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.21466431233520603,
66
+ "min": 0.12085397768418725,
67
+ "max": 0.29286830470550296,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8586572493408241,
72
+ "min": 0.483415910736749,
73
+ "max": 1.3729174195551404,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 25.613636363636363,
114
+ "min": 3.3863636363636362,
115
+ "max": 25.613636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1127.0,
120
+ "min": 149.0,
121
+ "max": 1394.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 25.613636363636363,
126
+ "min": 3.3863636363636362,
127
+ "max": 25.613636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1127.0,
132
+ "min": 149.0,
133
+ "max": 1394.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1679908422",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1679908882"
160
  },
161
+ "total": 460.14895640899977,
162
  "count": 1,
163
+ "self": 0.7895674730007158,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10292876199946477,
167
  "count": 1,
168
+ "self": 0.10292876199946477
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 459.2564601739996,
172
  "count": 1,
173
+ "self": 0.49016623697934847,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 5.846241936000297,
177
  "count": 1,
178
+ "self": 5.846241936000297
179
  },
180
  "TrainerController.advance": {
181
+ "total": 452.6829718790186,
182
+ "count": 18217,
183
+ "self": 0.263493961050699,
184
  "children": {
185
  "env_step": {
186
+ "total": 452.4194779179679,
187
+ "count": 18217,
188
+ "self": 329.18339330596154,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 122.98751471001287,
192
+ "count": 18217,
193
+ "self": 1.8901296979720428,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 121.09738501204083,
197
+ "count": 18217,
198
+ "self": 121.09738501204083
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.24856990199350548,
204
+ "count": 18217,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 457.74583978990995,
209
+ "count": 18217,
210
  "is_parallel": true,
211
+ "self": 223.41518318488306,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002092693000122381,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006417580016204738,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001450934998501907,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001450934998501907
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.034367600999758,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00047767500018380815,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003021359998456319,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003021359998456319
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.032102486999974644,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.032102486999974644
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0014853029997539124,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0003237099999751081,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0011615929997788044,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0011615929997788044
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 234.3306566050269,
271
+ "count": 18216,
272
  "is_parallel": true,
273
+ "self": 9.466481910018956,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.099213578037052,
277
+ "count": 18216,
278
  "is_parallel": true,
279
+ "self": 5.099213578037052
280
  },
281
  "communicator.exchange": {
282
+ "total": 189.53019968192984,
283
+ "count": 18216,
284
  "is_parallel": true,
285
+ "self": 189.53019968192984
286
  },
287
  "steps_from_proto": {
288
+ "total": 30.234761435041037,
289
+ "count": 18216,
290
  "is_parallel": true,
291
+ "self": 5.846674117066868,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 24.38808731797417,
295
+ "count": 182160,
296
  "is_parallel": true,
297
+ "self": 24.38808731797417
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 8.636000075057382e-05,
313
  "count": 1,
314
+ "self": 8.636000075057382e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 449.5033354977977,
324
+ "count": 385886,
325
  "is_parallel": true,
326
+ "self": 9.206752954598414,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 244.94867293820062,
330
+ "count": 385886,
331
  "is_parallel": true,
332
+ "self": 243.48391041620016,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.4647625220004556,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.4647625220004556
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 195.34790960499868,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 75.03490625402355,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 120.31300335097512,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 120.31300335097512
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.23699376200056577,
364
  "count": 1,
365
+ "self": 0.002571512000031362,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.2344222500005344,
369
  "count": 1,
370
+ "self": 0.2344222500005344
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.181818181818182,
8
- "creation_time": 1679902833.8099377,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 22.727272727272727,
17
- "creation_time": 1679902946.4722717,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.636363636363637,
26
- "creation_time": 1679903058.3628073,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.181818181818183,
35
- "creation_time": 1679903171.278404,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.181818181818183,
44
- "creation_time": 1679903171.431922,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 26.181818181818183,
54
- "creation_time": 1679903171.431922,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 13.909090909090908,
8
+ "creation_time": 1679908542.6574535,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
 
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 21.727272727272727,
17
+ "creation_time": 1679908655.6292062,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
 
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 23.90909090909091,
26
+ "creation_time": 1679908769.2580125,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
 
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 26.545454545454547,
35
+ "creation_time": 1679908881.3867598,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
 
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 26.545454545454547,
44
+ "creation_time": 1679908881.6471078,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
 
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 26.545454545454547,
54
+ "creation_time": 1679908881.6471078,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]