Hugging Face's logo

Ari8
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
Ari8 commited on
Commit
9a77934
·
verified ·
1 Parent(s): 756eea4

Second Push

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.1741887285.e1f1b82cdcfc.4685.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +4 -4
  16. run_logs/Player-0.log +14 -11
  17. run_logs/timers.json +115 -115
  18. run_logs/training_status.json +17 -26
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1115fd5a58e6d4cdc42622100320e5d00c67ece2d06abaa142273d6c175d05c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dabc74e467afbeb39452c52a05455a7a1dfeeee387ac7d1871f19b27fcf2c46e
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a735ec0ae075578381412502c97b456c02684a63c376e8c596bdd307e9b1ff6f
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0097b8ed5abc6674037a41919d1535006df3e1b7e09f2390f40a800ce704df79
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57fd00ecd5026ac9c395f689b520054e8a600cda6e696499918ec25d05381ce
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1115fd5a58e6d4cdc42622100320e5d00c67ece2d06abaa142273d6c175d05c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60af3f11deb153dc5bcd00f923ff7227b731a8432953d10ee5a9caa4a3d43c8f
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a388142a7a47a1df625a2d4136899574a7cd516d105578d8d2064913a9d8a036
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1115fd5a58e6d4cdc42622100320e5d00c67ece2d06abaa142273d6c175d05c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ebe5099bf5a9e85ab0291574d7280446b206a10e877f99586d9083b0a242f75
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2723201dcb64732a58593aa9965eb37fa23e43a2eab274fcbb78f45a1a96458a
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26377a70216df1e79087f1e031d838912688949242f80b5a9764b86536b0fb89
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e9dfde78630f6d1faa53b8a2aa41088056d70b3a398fd9c270940e23ceb517
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18d9fbd9e92d2581c5d21da181990d6bb3df37ab2251bb21eac12b0ae6d316e1
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91de8ebd3e1fc9f39bd3dd559eb8bcc0ab8677a1051d35270eb8a64100057a21
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bf757d96d0183b9411fe57e11b82774aeb4804b81692e86961717c37a9ba22c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93955583c7b96c68387c138fa360eabb8ba9e90a437817c87bf45ee749f9049
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ebf94d5a1f2472781fc6291d7123c253f3a20c44fcc5f7fc15b915d23ff8669
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b924976aa03c56ba1b5cf90b2c6cd528ac279b8b20bd34cc80cdfe517491e5
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a489e181eb91dbdd49dcd3cf304212ec2c2430ca8541dd129543f67ca159373e
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b16d39eadcb3335b7ab230c169d68085fe2f94d6b8282ec5c953cadaff6f63
3
  size 3849250
SnowballTarget/events.out.tfevents.1741887285.e1f1b82cdcfc.4685.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1848619b51fa744339d051269be19775302c88adfd6bbc0a462790908e98c8
3
+ size 23254
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": 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": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/content/ml-agents/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}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 20, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -5,11 +5,11 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
- learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
- num_epoch: 5
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
@@ -45,7 +45,7 @@ behaviors:
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
- env_path: /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
@@ -69,7 +69,7 @@ checkpoint_settings:
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
 
5
  hyperparameters:
6
  batch_size: 128
7
  buffer_size: 2048
8
+ learning_rate: 0.0001
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
+ num_epoch: 20
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
48
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
49
  env_args: null
50
  base_port: 5005
51
  num_envs: 1
 
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
run_logs/Player-0.log CHANGED
@@ -2,6 +2,9 @@ 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
  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
@@ -31,7 +34,7 @@ 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 0.126 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 +45,7 @@ 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: 0.832848 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.
@@ -166,23 +169,23 @@ Memory Statistics:
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
- Peak main deferred allocation count 36
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: [16.0 MB-32.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
- Peak Allocated memory 22.6 MB
179
- Peak Large allocation bytes 16.0 MB
180
  [ALLOC_DEFAULT_THREAD]
181
- Peak usage frame count: [1.0 MB-2.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
- Peak Allocated memory 1.8 MB
185
- Peak Large allocation bytes 0 B
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
188
  Used Block Count 1
@@ -210,10 +213,10 @@ 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]: 5214 frames, [64.0 KB-128.0 KB]: 244 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]: 5458 frames
 
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
  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 0.087 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
  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: 0.746441 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.
 
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
+ Peak main deferred allocation count 32
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]: 5458 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]: 5458 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
+ Peak Allocated memory 17.8 MB
188
+ Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
191
  Used Block Count 1
 
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]: 5009 frames, [64.0 KB-128.0 KB]: 449 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 67.3 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
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.0578773021697998,
6
- "min": 1.055963397026062,
7
- "max": 2.8262557983398438,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10054.06640625,
12
- "min": 10054.06640625,
13
- "max": 28850.419921875,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,74 +26,74 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 13.358370780944824,
30
- "min": 0.5474177002906799,
31
- "max": 13.366846084594727,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2604.88232421875,
36
- "min": 106.19903564453125,
37
- "max": 2726.836669921875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.06706652160218629,
42
- "min": 0.06408785938552361,
43
- "max": 0.07230623699190533,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.26826608640874516,
48
- "min": 0.2633850019810352,
49
- "max": 0.36153118495952663,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.17767062362502606,
54
- "min": 0.14134099037756265,
55
- "max": 0.29506417000994956,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.7106824945001042,
60
- "min": 0.5653639615102506,
61
- "max": 1.475320850049748,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 8.082097306000009e-06,
66
- "min": 8.082097306000009e-06,
67
- "max": 0.000291882002706,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 3.2328389224000035e-05,
72
- "min": 3.2328389224000035e-05,
73
- "max": 0.00138516003828,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
77
- "value": 0.10269399999999998,
78
- "min": 0.10269399999999998,
79
- "max": 0.197294,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.Epsilon.sum": {
83
- "value": 0.4107759999999999,
84
- "min": 0.4107759999999999,
85
  "max": 0.9617200000000001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
- "value": 0.0001444306000000001,
90
- "min": 0.0001444306000000001,
91
- "max": 0.004864970599999999,
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
  },
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 26.15909090909091,
114
- "min": 4.4772727272727275,
115
- "max": 26.363636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1151.0,
120
- "min": 197.0,
121
- "max": 1445.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 26.15909090909091,
126
- "min": 4.4772727272727275,
127
- "max": 26.363636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1151.0,
132
- "min": 197.0,
133
- "max": 1445.0,
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": "1741867790",
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 /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1741868302"
160
  },
161
- "total": 511.6199468909999,
162
  "count": 1,
163
- "self": 0.4380335749997357,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.02834533600002942,
167
  "count": 1,
168
- "self": 0.02834533600002942
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 511.15356798000016,
172
  "count": 1,
173
- "self": 0.39022323102949485,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.7577263589998893,
177
  "count": 1,
178
- "self": 2.7577263589998893
179
  },
180
  "TrainerController.advance": {
181
- "total": 507.9167060189707,
182
  "count": 18192,
183
- "self": 0.407388063998269,
184
  "children": {
185
  "env_step": {
186
- "total": 313.1282431159698,
187
  "count": 18192,
188
- "self": 238.19580122997263,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 74.6922903260022,
192
  "count": 18192,
193
- "self": 1.3334862909819094,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 73.35880403502028,
197
  "count": 18192,
198
- "self": 73.35880403502028
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2401515599949562,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 509.6798369899957,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 301.5434563090316,
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": 0.0027939240001160215,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0007773649999762711,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0020165590001397504,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0020165590001397504
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.07641948099990259,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006036269999185606,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003824479999821051,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003824479999821051
244
  },
245
  "communicator.exchange": {
246
- "total": 0.07352164400003858,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.07352164400003858
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019117619999633462,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0004206530004466913,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014911089995166549,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014911089995166549
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 208.13638068096407,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 9.618732209977225,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.338796489005745,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.338796489005745
280
  },
281
  "communicator.exchange": {
282
- "total": 161.30552959597344,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 161.30552959597344
286
  },
287
  "steps_from_proto": {
288
- "total": 31.873322386007658,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 5.843885477975618,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 26.02943690803204,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 26.02943690803204
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 194.38107483900262,
311
  "count": 18192,
312
- "self": 0.48761775202524404,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.478251229976877,
316
  "count": 18192,
317
- "self": 27.03985909997664,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.43839213000023847,
321
  "count": 4,
322
- "self": 0.43839213000023847
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 166.4152058570005,
328
  "count": 90,
329
- "self": 68.06163703099833,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 98.35356882600217,
333
- "count": 7645,
334
- "self": 98.35356882600217
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 9.330001375928987e-07,
344
  "count": 1,
345
- "self": 9.330001375928987e-07
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.08891143799996826,
349
  "count": 1,
350
- "self": 0.0011602550000588963,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.08775118299990936,
354
  "count": 1,
355
- "self": 0.08775118299990936
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8160785436630249,
6
+ "min": 0.8056858777999878,
7
+ "max": 2.8188047409057617,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7756.01025390625,
12
+ "min": 7756.01025390625,
13
+ "max": 28774.359375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.493075370788574,
30
+ "min": 0.46860674023628235,
31
+ "max": 13.493075370788574,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2631.149658203125,
36
+ "min": 90.90970611572266,
37
+ "max": 2729.76904296875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06561397178989223,
42
+ "min": 0.06561397178989223,
43
+ "max": 0.0721317074981016,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2624558871595689,
48
+ "min": 0.2624558871595689,
49
+ "max": 0.35400036197543244,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.18126209022696405,
54
+ "min": 0.14492982050219055,
55
+ "max": 0.26831477778799395,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7250483609078562,
60
+ "min": 0.5797192820087622,
61
+ "max": 1.3415738889399698,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 2.694097306000002e-06,
66
+ "min": 2.694097306000002e-06,
67
+ "max": 9.729400270600001e-05,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 1.0776389224000008e-05,
72
+ "min": 1.0776389224000008e-05,
73
+ "max": 0.00046172003828000015,
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": 0.9617200000000001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Beta.mean": {
89
+ "value": 0.00014443060000000012,
90
+ "min": 0.00014443060000000012,
91
+ "max": 0.0048649706,
92
  "count": 20
93
  },
94
  "SnowballTarget.Policy.Beta.sum": {
95
+ "value": 0.0005777224000000005,
96
+ "min": 0.0005777224000000005,
97
  "max": 0.023089828,
98
  "count": 20
99
  },
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.727272727272727,
114
+ "min": 4.909090909090909,
115
+ "max": 26.727272727272727,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1176.0,
120
+ "min": 216.0,
121
+ "max": 1443.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.727272727272727,
126
+ "min": 4.909090909090909,
127
+ "max": 26.727272727272727,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1176.0,
132
+ "min": 216.0,
133
+ "max": 1443.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1741887284",
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": "2.6.0+cu124",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1741888309"
160
  },
161
+ "total": 1024.3487001059998,
162
  "count": 1,
163
+ "self": 0.4366662509996786,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.023184963000062453,
167
  "count": 1,
168
+ "self": 0.023184963000062453
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 1023.888848892,
172
  "count": 1,
173
+ "self": 0.4495890470120685,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.047985283999992,
177
  "count": 1,
178
+ "self": 3.047985283999992
179
  },
180
  "TrainerController.advance": {
181
+ "total": 1020.2959722799878,
182
  "count": 18192,
183
+ "self": 0.45204846998626635,
184
  "children": {
185
  "env_step": {
186
+ "total": 328.9933967329998,
187
  "count": 18192,
188
+ "self": 249.43177767302006,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 79.30847023198737,
192
  "count": 18192,
193
+ "self": 1.4409570299700363,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 77.86751320201734,
197
  "count": 18192,
198
+ "self": 77.86751320201734
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2531488279923906,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 1022.247619267994,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 804.999536697996,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005260118999899532,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003596709000021292,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0016634099998782403,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0016634099998782403
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.036133128999949804,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00060663499994007,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000432909999972253,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000432909999972253
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03314065900008245,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03314065900008245
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0019529249999550302,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004045500002121116,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015483749997429186,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015483749997429186
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 217.24808256999802,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 10.279016690004823,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.707963745001166,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.707963745001166
280
  },
281
  "communicator.exchange": {
282
+ "total": 167.91120207000324,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 167.91120207000324
286
  },
287
  "steps_from_proto": {
288
+ "total": 33.34990006498879,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 6.230441138077595,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 27.119458926911193,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 27.119458926911193
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 690.8505270770017,
311
  "count": 18192,
312
+ "self": 0.5663526340157432,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 28.494085106987086,
316
  "count": 18192,
317
+ "self": 27.975418560987237,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.5186665459998494,
321
  "count": 4,
322
+ "self": 0.5186665459998494
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 661.7900893359989,
328
  "count": 90,
329
+ "self": 264.27605134198336,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 397.51403799401555,
333
+ "count": 30580,
334
+ "self": 397.51403799401555
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 9.980001323128818e-07,
344
  "count": 1,
345
+ "self": 9.980001323128818e-07
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.09530128300002616,
349
  "count": 1,
350
+ "self": 0.0009271900000840105,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.09437409299994215,
354
  "count": 1,
355
+ "self": 0.09437409299994215
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,25 +1,11 @@
1
  {
2
- "metadata": {
3
- "stats_format_version": "0.3.0",
4
- "mlagents_version": "1.2.0.dev0",
5
- "torch_version": "2.6.0+cu124"
6
- },
7
  "SnowballTarget": {
8
  "checkpoints": [
9
- {
10
- "steps": 0,
11
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.onnx",
12
- "reward": null,
13
- "creation_time": 1741867573.3569145,
14
- "auxillary_file_paths": [
15
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-0.pt"
16
- ]
17
- },
18
  {
19
  "steps": 49936,
20
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
21
- "reward": 19.818181818181817,
22
- "creation_time": 1741867921.5344663,
23
  "auxillary_file_paths": [
24
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
25
  ]
@@ -27,8 +13,8 @@
27
  {
28
  "steps": 99960,
29
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
30
- "reward": 24.0,
31
- "creation_time": 1741868048.7256975,
32
  "auxillary_file_paths": [
33
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
34
  ]
@@ -36,8 +22,8 @@
36
  {
37
  "steps": 149984,
38
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
39
- "reward": 26.0,
40
- "creation_time": 1741868175.7416704,
41
  "auxillary_file_paths": [
42
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
43
  ]
@@ -45,8 +31,8 @@
45
  {
46
  "steps": 199984,
47
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
48
- "reward": 26.727272727272727,
49
- "creation_time": 1741868301.9919586,
50
  "auxillary_file_paths": [
51
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
52
  ]
@@ -54,8 +40,8 @@
54
  {
55
  "steps": 200112,
56
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
57
- "reward": 26.727272727272727,
58
- "creation_time": 1741868302.0920796,
59
  "auxillary_file_paths": [
60
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
61
  ]
@@ -64,11 +50,16 @@
64
  "final_checkpoint": {
65
  "steps": 200112,
66
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
67
- "reward": 26.727272727272727,
68
- "creation_time": 1741868302.0920796,
69
  "auxillary_file_paths": [
70
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
71
  ]
72
  }
 
 
 
 
 
73
  }
74
  }
 
1
  {
 
 
 
 
 
2
  "SnowballTarget": {
3
  "checkpoints": [
 
 
 
 
 
 
 
 
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 19.09090909090909,
8
+ "creation_time": 1741887535.5588148,
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": 25.545454545454547,
17
+ "creation_time": 1741887795.1287668,
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": 26.181818181818183,
26
+ "creation_time": 1741888054.6773994,
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": 26.818181818181817,
35
+ "creation_time": 1741888308.7917597,
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": 26.818181818181817,
44
+ "creation_time": 1741888308.8995469,
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": 26.818181818181817,
54
+ "creation_time": 1741888308.8995469,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
+ },
60
+ "metadata": {
61
+ "stats_format_version": "0.3.0",
62
+ "mlagents_version": "1.2.0.dev0",
63
+ "torch_version": "2.6.0+cu124"
64
  }
65
  }