Hugging Face's logo

younus00
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
younus00 commited on
Commit
9a6452d
·
verified ·
1 Parent(s): 180132e

First Push

Browse files
Files changed (15) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-349944.onnx +3 -0
  3. SnowballTarget/SnowballTarget-349944.pt +3 -0
  4. SnowballTarget/SnowballTarget-399968.onnx +3 -0
  5. SnowballTarget/SnowballTarget-399968.pt +3 -0
  6. SnowballTarget/SnowballTarget-400224.onnx +3 -0
  7. SnowballTarget/SnowballTarget-400224.pt +3 -0
  8. SnowballTarget/checkpoint.pt +1 -1
  9. SnowballTarget/events.out.tfevents.1756991605.79c145200075.9177.0 +3 -0
  10. SnowballTarget/events.out.tfevents.1756991829.79c145200075.10190.0 +3 -0
  11. config.json +1 -1
  12. configuration.yaml +2 -2
  13. run_logs/Player-0.log +14 -17
  14. run_logs/timers.json +163 -163
  15. run_logs/training_status.json +19 -19
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d70bdf3768496e4cd98faca523af88ccfc6671856bbbdb69aedb0fa45de000f0
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513bcc41b3dbdf8136e0d1b8fa675dfaa8303ffcb22d6bac6cd281fd1e53e257
3
  size 650646
SnowballTarget/SnowballTarget-349944.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a1b354c0354a0f824922276c11b3c61867fe65307118f2e561519ca593512e
3
+ size 650646
SnowballTarget/SnowballTarget-349944.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a9bd6d2c2e9ee4a4c2ec4017d9572a0bdebb2ae70f24bfebb7d6ee27e9c71d
3
+ size 3850564
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513bcc41b3dbdf8136e0d1b8fa675dfaa8303ffcb22d6bac6cd281fd1e53e257
3
+ size 650646
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffb11a3bc827b1f59ee4d47c4d498bc9d91282036cd6f202a6919eba5871c8b
3
+ size 3850564
SnowballTarget/SnowballTarget-400224.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513bcc41b3dbdf8136e0d1b8fa675dfaa8303ffcb22d6bac6cd281fd1e53e257
3
+ size 650646
SnowballTarget/SnowballTarget-400224.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f629e81f60480296a038333ecd8563e37a94fc0425c85fa034b8b8371e9e64c
3
+ size 3850564
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:163cfe0a2fa38efdc1c5316e39148d22d73fccc216210990dbca12653fa0e8a8
3
  size 3849717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a3d1cdf3c2adc86c0de913a16a82c259861afa3d3375cd132259b38e7bf8bb
3
  size 3849717
SnowballTarget/events.out.tfevents.1756991605.79c145200075.9177.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53ac58fd74a4b3355f5e5e66a70699929281b744ffb4d922f48bb532b946fed
3
+ size 9302
SnowballTarget/events.out.tfevents.1756991829.79c145200075.10190.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a8b088e287a019cea9308ec75cd3a5535b8d71c437ba934217a5f3218f1472
3
+ size 9254
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": 3, "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": 3, "even_checkpoints": false, "max_steps": 400000, "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
@@ -38,7 +38,7 @@ behaviors:
38
  init_path: null
39
  keep_checkpoints: 3
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: false
@@ -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
 
38
  init_path: null
39
  keep_checkpoints: 3
40
  even_checkpoints: false
41
+ max_steps: 400000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: 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 0.118 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 1.092681 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]: 5367 frames, [16.0 KB-32.0 KB]: 90 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
@@ -175,16 +172,16 @@ Memory Statistics:
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]: 5458 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.5 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.9 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]: 5187 frames, [64.0 KB-128.0 KB]: 271 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 66.4 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 5458 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]: 5458 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]: 5457 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]: 5458 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]: 5458 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 0.078 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: 0.627832 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]: 2674 frames, [16.0 KB-32.0 KB]: 45 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
 
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]: 2720 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.4 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 2720 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.4 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]: 2656 frames, [64.0 KB-128.0 KB]: 64 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 2720 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]: 2720 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]: 2719 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]: 2720 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]: 2720 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": 0.9146209359169006,
6
- "min": 0.9146209359169006,
7
- "max": 2.8359427452087402,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8692.5576171875,
12
- "min": 8692.5576171875,
13
- "max": 28949.302734375,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
- "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
- "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.181785583496094,
30
- "min": 0.2459767907857895,
31
- "max": 13.181785583496094,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2570.4482421875,
36
- "min": 47.71949768066406,
37
- "max": 2664.17333984375,
38
- "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06889598609140032,
42
- "min": 0.06156179365536766,
43
- "max": 0.07375732224432331,
44
- "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.2755839443656013,
48
- "min": 0.24624717462147064,
49
- "max": 0.36010166561458856,
50
- "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.20456148201928417,
54
- "min": 0.12234620247310135,
55
- "max": 0.301071326668356,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.8182459280771367,
60
- "min": 0.4893848098924054,
61
- "max": 1.481400996738789,
62
- "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000005e-06,
66
- "min": 8.082097306000005e-06,
67
- "max": 0.000291882002706,
68
- "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.232838922400002e-05,
72
- "min": 3.232838922400002e-05,
73
- "max": 0.00138516003828,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269400000000001,
78
- "min": 0.10269400000000001,
79
- "max": 0.19729400000000002,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.41077600000000003,
84
- "min": 0.41077600000000003,
85
- "max": 0.96172,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.0048649706,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
- "value": 0.0005777224000000004,
96
- "min": 0.0005777224000000004,
97
- "max": 0.023089828,
98
- "count": 20
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
- "count": 20
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
- "value": 8756.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.022727272727273,
114
- "min": 3.1136363636363638,
115
- "max": 26.022727272727273,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1145.0,
120
- "min": 137.0,
121
- "max": 1420.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.022727272727273,
126
- "min": 3.1136363636363638,
127
- "max": 26.022727272727273,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1145.0,
132
- "min": 137.0,
133
- "max": 1420.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1756990740",
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": "1756991159"
160
  },
161
- "total": 419.32921720900003,
162
  "count": 1,
163
- "self": 0.43598514200016325,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.035967831999869304,
167
  "count": 1,
168
- "self": 0.035967831999869304
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 418.857264235,
172
  "count": 1,
173
- "self": 0.3514050890021281,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 3.3849073230001068,
177
  "count": 1,
178
- "self": 3.3849073230001068
179
  },
180
  "TrainerController.advance": {
181
- "total": 415.0412834769977,
182
- "count": 18192,
183
- "self": 0.39409950202457367,
184
  "children": {
185
  "env_step": {
186
- "total": 295.14743728898384,
187
- "count": 18192,
188
- "self": 228.38597882198724,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 66.53406697701621,
192
- "count": 18192,
193
- "self": 1.2777624280204236,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 65.25630454899579,
197
- "count": 18192,
198
- "self": 65.25630454899579
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.22739148998039127,
204
- "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 417.4396961739892,
209
- "count": 18192,
210
  "is_parallel": true,
211
- "self": 217.90085437798052,
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": 0.005785830000149872,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004068326999913552,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.00171750300023632,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.00171750300023632
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.041414103999841245,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006291859999691951,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003783039999234461,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003783039999234461
244
  },
245
  "communicator.exchange": {
246
- "total": 0.032607522000034805,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.032607522000034805
250
  },
251
  "steps_from_proto": {
252
- "total": 0.007799091999913799,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00043356399964977754,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.007365528000264021,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.007365528000264021
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 199.53884179600868,
271
- "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.047360739990609,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.339401477012416,
277
- "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.339401477012416
280
  },
281
  "communicator.exchange": {
282
- "total": 153.36032491501237,
283
- "count": 18191,
284
  "is_parallel": true,
285
- "self": 153.36032491501237
286
  },
287
  "steps_from_proto": {
288
- "total": 30.791754663993288,
289
- "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.486311956942245,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 25.305442707051043,
295
- "count": 181910,
296
  "is_parallel": true,
297
- "self": 25.305442707051043
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 119.4997466859893,
311
- "count": 18192,
312
- "self": 0.4588698919912986,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 26.675244468997562,
316
- "count": 18192,
317
- "self": 26.240160909997485,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.435083559000077,
321
- "count": 4,
322
- "self": 0.435083559000077
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 92.36563232500043,
328
- "count": 90,
329
- "self": 37.19088479100401,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 55.174747533996424,
333
- "count": 4587,
334
- "self": 55.174747533996424
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 8.910001270123757e-07,
344
  "count": 1,
345
- "self": 8.910001270123757e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.07966745499993522,
349
  "count": 1,
350
- "self": 0.000875173999929757,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.07879228100000546,
354
  "count": 1,
355
- "self": 0.07879228100000546
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6695061922073364,
6
+ "min": 0.6695061922073364,
7
+ "max": 0.7076132297515869,
8
+ "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6421.9033203125,
12
+ "min": 6421.9033203125,
13
+ "max": 7196.74609375,
14
+ "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 399968.0,
18
+ "min": 309960.0,
19
+ "max": 399968.0,
20
+ "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 399968.0,
24
+ "min": 309960.0,
25
+ "max": 399968.0,
26
+ "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.663859367370605,
30
+ "min": 13.427301406860352,
31
+ "max": 13.678183555603027,
32
+ "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2787.42724609375,
36
+ "min": 2504.504638671875,
37
+ "max": 2787.42724609375,
38
+ "count": 10
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06654974156237373,
42
+ "min": 0.06190739900347241,
43
+ "max": 0.07329449321660636,
44
+ "count": 10
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.3327487078118686,
48
+ "min": 0.24762959601388965,
49
+ "max": 0.36048221033678257,
50
+ "count": 10
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.18489841824653103,
54
+ "min": 0.17032056338354654,
55
+ "max": 0.18976850397245704,
56
+ "count": 10
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.9244920912326551,
60
+ "min": 0.6812822535341861,
61
+ "max": 0.9244920912326551,
62
+ "count": 10
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 3.726098758000003e-06,
66
+ "min": 3.726098758000003e-06,
67
+ "max": 7.055107648299998e-05,
68
+ "count": 10
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 1.8630493790000015e-05,
72
+ "min": 1.8630493790000015e-05,
73
+ "max": 0.00028263040579,
74
+ "count": 10
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
+ "value": 0.10124200000000001,
78
+ "min": 0.10124200000000001,
79
+ "max": 0.12351700000000002,
80
+ "count": 10
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
+ "value": 0.50621,
84
+ "min": 0.414868,
85
+ "max": 0.59421,
86
+ "count": 10
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 7.197580000000004e-05,
90
+ "min": 7.197580000000004e-05,
91
+ "max": 0.0011834983000000002,
92
+ "count": 10
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.00035987900000000023,
96
+ "min": 0.00035987900000000023,
97
+ "max": 0.004751079000000001,
98
+ "count": 10
99
  },
100
  "SnowballTarget.Environment.EpisodeLength.mean": {
101
  "value": 199.0,
102
  "min": 199.0,
103
  "max": 199.0,
104
+ "count": 10
105
  },
106
  "SnowballTarget.Environment.EpisodeLength.sum": {
107
+ "value": 10945.0,
108
  "min": 8756.0,
109
  "max": 10945.0,
110
+ "count": 10
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.327272727272728,
114
+ "min": 26.113636363636363,
115
+ "max": 27.227272727272727,
116
+ "count": 10
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1448.0,
120
+ "min": 1149.0,
121
+ "max": 1472.0,
122
+ "count": 10
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.327272727272728,
126
+ "min": 26.113636363636363,
127
+ "max": 27.227272727272727,
128
+ "count": 10
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1448.0,
132
+ "min": 1149.0,
133
+ "max": 1472.0,
134
+ "count": 10
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1756991829",
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": "1756992028"
160
  },
161
+ "total": 199.33305670500022,
162
  "count": 1,
163
+ "self": 0.43519101100037005,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.02341207299969028,
167
  "count": 1,
168
+ "self": 0.02341207299969028
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 198.87445362100016,
172
  "count": 1,
173
+ "self": 0.15536558302801495,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9229447759998948,
177
  "count": 1,
178
+ "self": 1.9229447759998948
179
  },
180
  "TrainerController.advance": {
181
+ "total": 196.71605170597286,
182
+ "count": 9064,
183
+ "self": 0.1656704029901448,
184
  "children": {
185
  "env_step": {
186
+ "total": 139.6038688800095,
187
+ "count": 9064,
188
+ "self": 107.45362392401876,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 32.052408460002425,
192
+ "count": 9064,
193
+ "self": 0.5862241830118364,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 31.46618427699059,
197
+ "count": 9064,
198
+ "self": 31.46618427699059
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.0978364959883038,
204
+ "count": 9064,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 198.1561156289954,
209
+ "count": 9064,
210
  "is_parallel": true,
211
+ "self": 103.54951392197336,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.00195648999988407,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005927139995947073,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013637760002893629,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013637760002893629
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03366092699980072,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005698909994862333,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0003696080002555391,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0003696080002555391
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.030947068999921612,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.030947068999921612
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0017743590001373377,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00033496299965918297,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0014393960004781547,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0014393960004781547
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 94.60660170702204,
271
+ "count": 9063,
272
  "is_parallel": true,
273
+ "self": 4.638142214032541,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 2.5067467330027284,
277
+ "count": 9063,
278
  "is_parallel": true,
279
+ "self": 2.5067467330027284
280
  },
281
  "communicator.exchange": {
282
+ "total": 72.62902093002276,
283
+ "count": 9063,
284
  "is_parallel": true,
285
+ "self": 72.62902093002276
286
  },
287
  "steps_from_proto": {
288
+ "total": 14.832691829964006,
289
+ "count": 9063,
290
  "is_parallel": true,
291
+ "self": 2.5560702369321007,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 12.276621593031905,
295
+ "count": 90630,
296
  "is_parallel": true,
297
+ "self": 12.276621593031905
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 56.94651242297323,
311
+ "count": 9064,
312
+ "self": 0.18030551794663552,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 12.464642225026637,
316
+ "count": 9064,
317
+ "self": 12.274451350026993,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.1901908749996437,
321
+ "count": 2,
322
+ "self": 0.1901908749996437
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 44.301564679999956,
328
+ "count": 45,
329
+ "self": 17.995614425003623,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 26.305950254996333,
333
+ "count": 2292,
334
+ "self": 26.305950254996333
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 8.509996405337006e-07,
344
  "count": 1,
345
+ "self": 8.509996405337006e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.08009070499974769,
349
  "count": 1,
350
+ "self": 0.0009527509996587469,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.07913795400008894,
354
  "count": 1,
355
+ "self": 0.07913795400008894
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,40 +2,40 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 149984,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
7
- "reward": 24.09090909090909,
8
- "creation_time": 1756991056.6121058,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
11
  ]
12
  },
13
  {
14
- "steps": 199984,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
16
- "reward": 26.363636363636363,
17
- "creation_time": 1756991159.412219,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
20
  ]
21
  },
22
  {
23
- "steps": 200112,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
25
- "reward": 26.363636363636363,
26
- "creation_time": 1756991159.5040152,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
  }
31
  ],
32
  "final_checkpoint": {
33
- "steps": 200112,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
- "reward": 26.363636363636363,
36
- "creation_time": 1756991159.5040152,
37
  "auxillary_file_paths": [
38
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
39
  ]
40
  }
41
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 349944,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.onnx",
7
+ "reward": 26.181818181818183,
8
+ "creation_time": 1756991927.809361,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 399968,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
16
+ "reward": 25.727272727272727,
17
+ "creation_time": 1756992027.9354646,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 400224,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.onnx",
25
+ "reward": 25.727272727272727,
26
+ "creation_time": 1756992028.0366032,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
29
  ]
30
  }
31
  ],
32
  "final_checkpoint": {
33
+ "steps": 400224,
34
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
35
+ "reward": 25.727272727272727,
36
+ "creation_time": 1756992028.0366032,
37
  "auxillary_file_paths": [
38
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-400224.pt"
39
  ]
40
  }
41
  },