Hugging Face's logo

AndrewL088
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
AndrewL088 commited on
Commit
b70a6de
·
1 Parent(s): 76de0bb

First Push 20230903

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +1 -1
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +1 -1
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +1 -1
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +1 -1
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +1 -1
  12. SnowballTarget/checkpoint.pt +1 -1
  13. SnowballTarget/events.out.tfevents.1693712205.09468539c3fd.11481.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +3 -3
  16. run_logs/Player-0.log +14 -14
  17. run_logs/timers.json +116 -116
  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:e5b8a0c2674b7a1d8c3039bf02886d65828af0f6cfd0d612f8b56fe9bac20077
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6406c6c92ac7735255fc8d5ed6a562eca73e93768095679472b270f32ad408
3
  size 910131
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7731e5ec04a3460bde64e1a1b2f82fb8e222b4dcf4e5e8da45f93eab55ae82fe
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933f0ba5c7a0e2c66ef7db8301ca766f574d4e8a5caf4888489269a4775446e3
3
  size 910131
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a744a46e49380a30a6241af583011daf75b69eab8ad849cee6cafda051f3820
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a60cf4108d0f801d90ca9881cc90474665ec1efaa9831fd916bf49333d5d4a7
3
  size 5426908
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b8a0c2674b7a1d8c3039bf02886d65828af0f6cfd0d612f8b56fe9bac20077
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6406c6c92ac7735255fc8d5ed6a562eca73e93768095679472b270f32ad408
3
  size 910131
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ad7583ae8121e1f9ca29fe33323586892c43af0db6be36a7d5e68a1ecf9699d
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990b172be1bd79fd68959d58885f8e5d7e25d7dc687afe6660ecc155931ea9c8
3
  size 5426908
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5b8a0c2674b7a1d8c3039bf02886d65828af0f6cfd0d612f8b56fe9bac20077
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6406c6c92ac7735255fc8d5ed6a562eca73e93768095679472b270f32ad408
3
  size 910131
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3968d8f4a66e940c261cb3f565e865f1a3ff02d090328f49bfaa197cf924a84
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4976e6cddb0075cd72ab42dd10a498306d8026611a184f3e10f4f6dc030170e
3
  size 5426908
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fcbb70a5e3536f17af005465a6dcc9db497caf897ac2c0ce0fc3d9a06d4b9a0
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9570afe177cd9aef4f6f7cc30ab762342e96f49830d2bdd55f691618c5c1326f
3
  size 910131
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:818870a180e22254376a9ff27243c0cb7b6cf7e8b75897353702dcc0112a5ccf
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e18f5796d124159cf5c57fed67cb00fae6a6f407ee7da62c96d49d89044ce6c
3
  size 5426908
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d86e06b99a632e43eaa2b8e3e4079af5abd2b952b802eca56eeebc3597ab0f2
3
  size 910131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8077baceb571204fceb4a505cfdae371cb1702aa7520dd137c1f675dbaa90057
3
  size 910131
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:615fe267f71b40f61a7fdad3d2ccf6f076f8e5834f903823d109cdc3402281cf
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e5123d0e67448e3e3637219e6335c84fcc9955ec4e8aebcd036a7ccd1eef445
3
  size 5426908
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3968d8f4a66e940c261cb3f565e865f1a3ff02d090328f49bfaa197cf924a84
3
  size 5426908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4976e6cddb0075cd72ab42dd10a498306d8026611a184f3e10f4f6dc030170e
3
  size 5426908
SnowballTarget/events.out.tfevents.1693712205.09468539c3fd.11481.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0c6e6ce8c30607f9b5d351efd561e26c359c745f698739e5cadb6a363a74f0
3
+ size 28845
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.19, "lambd": 0.96, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.985, "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}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.15, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.98, "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
@@ -7,8 +7,8 @@ behaviors:
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
- epsilon: 0.19
11
- lambd: 0.96
12
  num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
@@ -25,7 +25,7 @@ behaviors:
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
- gamma: 0.985
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
 
7
  buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
+ epsilon: 0.15
11
+ lambd: 0.95
12
  num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
 
25
  deterministic: false
26
  reward_signals:
27
  extrinsic:
28
+ gamma: 0.98
29
  strength: 1.0
30
  network_settings:
31
  normalize: false
run_logs/Player-0.log CHANGED
@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
- - Completed reload, in 0.080 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)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
- UnloadTime: 0.649708 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
- Peak usage frame count: [8.0 KB-16.0 KB]: 5369 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
@@ -166,19 +166,19 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 46
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]: 5461 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 6.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 MB
@@ -210,13 +210,13 @@ Memory Statistics:
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
- Peak usage frame count: [32.0 KB-64.0 KB]: 4649 frames, [64.0 KB-128.0 KB]: 812 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
- Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
- Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ Memory Statistics:
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 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]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
@@ -246,13 +246,13 @@ Memory Statistics:
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
- Peak usage frame count: [0-1.0 KB]: 5461 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]: 5461 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.090 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: 0.631500 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]: 5375 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 44
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]: 5467 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.8 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5467 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]: 4261 frames, [64.0 KB-128.0 KB]: 1206 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5467 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]: 5467 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]: 5466 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]: 5467 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]: 5467 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": 0.8666054606437683,
6
- "min": 0.8666054606437683,
7
- "max": 2.864396095275879,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8283.8818359375,
12
- "min": 8283.8818359375,
13
- "max": 29334.28125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 8.750391006469727,
30
- "min": 0.48306259512901306,
31
- "max": 8.750391006469727,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1706.326171875,
36
- "min": 93.71414184570312,
37
- "max": 1761.9444580078125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.10000485768404735,
54
- "min": 0.09217458232427388,
55
- "max": 0.10287201129217198,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.4000194307361894,
60
- "min": 0.3686983292970955,
61
- "max": 0.5143600564608599,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.19882501185159474,
66
- "min": 0.13165385580742847,
67
- "max": 0.2862656643636086,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7953000474063789,
72
- "min": 0.5266154232297139,
73
- "max": 1.431328321818043,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -86,15 +86,15 @@
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10242460000000003,
90
- "min": 0.10242460000000003,
91
- "max": 0.1875646,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.40969840000000013,
96
- "min": 0.40969840000000013,
97
- "max": 0.915548,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.75,
114
- "min": 3.7954545454545454,
115
- "max": 25.75,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1133.0,
120
- "min": 167.0,
121
- "max": 1413.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.75,
126
- "min": 3.7954545454545454,
127
- "max": 25.75,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1133.0,
132
- "min": 167.0,
133
- "max": 1413.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1693711121",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
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",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1693711797"
160
  },
161
- "total": 676.400114911,
162
  "count": 1,
163
- "self": 0.43580603500004145,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.040644914000040444,
167
  "count": 1,
168
- "self": 0.040644914000040444
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 675.9236639619999,
172
  "count": 1,
173
- "self": 0.6265558650104595,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.8728851329999543,
177
  "count": 1,
178
- "self": 3.8728851329999543
179
  },
180
  "TrainerController.advance": {
181
- "total": 671.2531152669894,
182
- "count": 18202,
183
- "self": 0.31760299799384484,
184
  "children": {
185
  "env_step": {
186
- "total": 670.9355122689956,
187
- "count": 18202,
188
- "self": 538.4037770119614,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 132.2177223850224,
192
- "count": 18202,
193
- "self": 1.8529336860233343,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 130.36478869899906,
197
- "count": 18202,
198
- "self": 130.36478869899906
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.31401287201174455,
204
- "count": 18202,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 674.2581598209763,
209
- "count": 18202,
210
  "is_parallel": true,
211
- "self": 399.8941451639748,
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": 0.002082613000084166,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0006806989997585333,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0014019140003256325,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0014019140003256325
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.05155504100002872,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00043253700027889863,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004153689999384369,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004153689999384369
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04840907299990249,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04840907299990249
250
  },
251
  "steps_from_proto": {
252
- "total": 0.002298061999908896,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00048346899961870804,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0018145930002901878,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0018145930002901878
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 274.36401465700146,
271
- "count": 18201,
272
  "is_parallel": true,
273
- "self": 11.614174686070328,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.108010712970554,
277
- "count": 18201,
278
  "is_parallel": true,
279
- "self": 6.108010712970554
280
  },
281
  "communicator.exchange": {
282
- "total": 214.97144132797916,
283
- "count": 18201,
284
  "is_parallel": true,
285
- "self": 214.97144132797916
286
  },
287
  "steps_from_proto": {
288
- "total": 41.670387929981416,
289
- "count": 18201,
290
  "is_parallel": true,
291
- "self": 7.847679237960165,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 33.82270869202125,
295
- "count": 182010,
296
  "is_parallel": true,
297
- "self": 33.82270869202125
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00019276000011814176,
313
  "count": 1,
314
- "self": 0.00019276000011814176,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 666.9883266647983,
324
- "count": 460186,
325
  "is_parallel": true,
326
- "self": 11.662097347823646,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 282.03350384797477,
330
- "count": 460186,
331
  "is_parallel": true,
332
- "self": 280.66964899097457,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.3638548570002058,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 1.3638548570002058
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 373.29272546899983,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 115.84347159701178,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 257.44925387198805,
350
  "count": 15295,
351
  "is_parallel": true,
352
- "self": 257.44925387198805
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.17091493699990679,
364
  "count": 1,
365
- "self": 0.0015689039996686915,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.1693460330002381,
369
  "count": 1,
370
- "self": 0.1693460330002381
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.1552319526672363,
6
+ "min": 1.1552319526672363,
7
+ "max": 2.872316360473633,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 11042.8623046875,
12
+ "min": 11042.8623046875,
13
+ "max": 29446.98828125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 6.402102947235107,
30
+ "min": 0.2349742352962494,
31
+ "max": 6.46518611907959,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1248.4100341796875,
36
+ "min": 45.58500289916992,
37
+ "max": 1318.89794921875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.09791296802822591,
54
+ "min": 0.09303315661127273,
55
+ "max": 0.10604800490235741,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.39165187211290364,
60
+ "min": 0.37213262644509093,
61
+ "max": 0.5154216504078624,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.17685941331745947,
66
+ "min": 0.10634225930042446,
67
+ "max": 0.2128629582331461,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.7074376532698379,
72
+ "min": 0.42536903720169783,
73
+ "max": 1.0641498260638294,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10134700000000002,
90
+ "min": 0.10134700000000002,
91
+ "max": 0.148647,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.4053880000000001,
96
+ "min": 0.4053880000000001,
97
+ "max": 0.7308600000000001,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 24.613636363636363,
114
+ "min": 3.4545454545454546,
115
+ "max": 25.381818181818183,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1083.0,
120
+ "min": 152.0,
121
+ "max": 1396.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 24.613636363636363,
126
+ "min": 3.4545454545454546,
127
+ "max": 25.381818181818183,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1083.0,
132
+ "min": 152.0,
133
+ "max": 1396.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1693712204",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
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",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1693712877"
160
  },
161
+ "total": 673.325666313,
162
  "count": 1,
163
+ "self": 0.7026468480003132,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.040508010999928956,
167
  "count": 1,
168
+ "self": 0.040508010999928956
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 672.5825114539998,
172
  "count": 1,
173
+ "self": 0.6361034939945966,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.9397197879998203,
177
  "count": 1,
178
+ "self": 3.9397197879998203
179
  },
180
  "TrainerController.advance": {
181
+ "total": 667.6996789210052,
182
+ "count": 18222,
183
+ "self": 0.3205168710092039,
184
  "children": {
185
  "env_step": {
186
+ "total": 667.379162049996,
187
+ "count": 18222,
188
+ "self": 534.7089586350535,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 132.35376623499496,
192
+ "count": 18222,
193
+ "self": 1.851569437942544,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 130.50219679705242,
197
+ "count": 18222,
198
+ "self": 130.50219679705242
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.31643717994757026,
204
+ "count": 18222,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 670.617412964978,
209
+ "count": 18222,
210
  "is_parallel": true,
211
+ "self": 391.44799577496815,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0021178430001782544,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006015479993948247,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015162950007834297,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015162950007834297
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.05535302899988892,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000711471000158781,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00034696300008363323,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00034696300008363323
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.05176436500005366,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.05176436500005366
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002530229999592848,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0005589999987023475,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0019712300008905004,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0019712300008905004
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 279.1694171900099,
271
+ "count": 18221,
272
  "is_parallel": true,
273
+ "self": 11.73278946598839,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 6.058035436011778,
277
+ "count": 18221,
278
  "is_parallel": true,
279
+ "self": 6.058035436011778
280
  },
281
  "communicator.exchange": {
282
+ "total": 219.4567923779996,
283
+ "count": 18221,
284
  "is_parallel": true,
285
+ "self": 219.4567923779996
286
  },
287
  "steps_from_proto": {
288
+ "total": 41.92179991001012,
289
+ "count": 18221,
290
  "is_parallel": true,
291
+ "self": 7.854247349979687,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 34.067552560030435,
295
+ "count": 182210,
296
  "is_parallel": true,
297
+ "self": 34.067552560030435
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00014054100029170513,
313
  "count": 1,
314
+ "self": 0.00014054100029170513,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 663.4952208280688,
324
+ "count": 469931,
325
  "is_parallel": true,
326
+ "self": 11.36439237806053,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 284.41271324400986,
330
+ "count": 469931,
331
  "is_parallel": true,
332
+ "self": 282.4649860440095,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.9477272000003722,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 1.9477272000003722
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 367.7181152059984,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 113.55896686299684,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 254.15914834300156,
350
  "count": 15295,
351
  "is_parallel": true,
352
+ "self": 254.15914834300156
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.3068687099998897,
364
  "count": 1,
365
+ "self": 0.003447293000135687,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.303421416999754,
369
  "count": 1,
370
+ "self": 0.303421416999754
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": 16.09090909090909,
8
- "creation_time": 1693711293.3008404,
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": 23.181818181818183,
17
- "creation_time": 1693711461.934057,
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": 24.727272727272727,
26
- "creation_time": 1693711631.9141142,
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": 26.09090909090909,
35
- "creation_time": 1693711796.801282,
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": 26.09090909090909,
44
- "creation_time": 1693711797.0056005,
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": 26.09090909090909,
54
- "creation_time": 1693711797.0056005,
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": 12.363636363636363,
8
+ "creation_time": 1693712377.0966704,
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": 17.90909090909091,
17
+ "creation_time": 1693712545.1410387,
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": 23.818181818181817,
26
+ "creation_time": 1693712714.5892131,
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": 24.454545454545453,
35
+ "creation_time": 1693712876.8540528,
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": 24.454545454545453,
44
+ "creation_time": 1693712877.1870134,
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": 24.454545454545453,
54
+ "creation_time": 1693712877.1870134,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]