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
406861d
·
verified ·
1 Parent(s): 9a77934

New 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.1741888792.e1f1b82cdcfc.10982.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +5 -8
  17. run_logs/timers.json +104 -104
  18. run_logs/training_status.json +23 -23
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe858648bff022b80e77dc75401c4dd905390b6c4cec74ba0dc1e462f9ff5e3
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a735ec0ae075578381412502c97b456c02684a63c376e8c596bdd307e9b1ff6f
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0769f4a85f8ecb1efec12f55cc8946af0b81b277065ac9f24564bff134bbe867
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57fd00ecd5026ac9c395f689b520054e8a600cda6e696499918ec25d05381ce
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e84909680321ffac0744ac6a7f98e1b3470b45041782b157a922c8ec692d5ee
3
  size 3850075
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe858648bff022b80e77dc75401c4dd905390b6c4cec74ba0dc1e462f9ff5e3
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a388142a7a47a1df625a2d4136899574a7cd516d105578d8d2064913a9d8a036
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e094dafc22e1f6b4df719ede68d204610ac51c1a413a60046ac8881547e11db2
3
  size 3850075
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84304ea54c7cd8b8961bc2e68b822db531ff3ec7d34fb2162b73fc912b161bb9
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe858648bff022b80e77dc75401c4dd905390b6c4cec74ba0dc1e462f9ff5e3
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2723201dcb64732a58593aa9965eb37fa23e43a2eab274fcbb78f45a1a96458a
3
  size 3850075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c28e26bb18eb1757757d082fe273b943134007b9ad2e078eaa3987a1ede78a4
3
  size 3850075
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54e9dfde78630f6d1faa53b8a2aa41088056d70b3a398fd9c270940e23ceb517
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6753883c1a50aba9abce1b7596870d23d0e5857d99c6dc1e89bdba9f2ea6a
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91de8ebd3e1fc9f39bd3dd559eb8bcc0ab8677a1051d35270eb8a64100057a21
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d54d19a4cde43860e1c5bf07b0ad020744c9efbb4f4624e5c1f9bb85beb4d1c
3
  size 3850000
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c93955583c7b96c68387c138fa360eabb8ba9e90a437817c87bf45ee749f9049
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2dec288135076c57b704ccca054f04e09a43a597685460cc9a97ed45cd91b8d
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98b924976aa03c56ba1b5cf90b2c6cd528ac279b8b20bd34cc80cdfe517491e5
3
  size 3850000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c357bf99fc9e3032e4b2363412a4aff1e72c9782f5b04dbf4ac83617304851
3
  size 3850000
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1b16d39eadcb3335b7ab230c169d68085fe2f94d6b8282ec5c953cadaff6f63
3
  size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221f9fd5083417c6f006022983fac8b4590932c799c7fe739929cba170b0fa09
3
  size 3849250
SnowballTarget/events.out.tfevents.1741888792.e1f1b82cdcfc.10982.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f334e8d55b38216be9250c1a9ff21a28314d170ff1db69e01353f93846af3a26
3
+ size 23686
config.json CHANGED
@@ -1 +1 @@
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}
 
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": 80, "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": "SnowballTarget2", "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
@@ -9,7 +9,7 @@ behaviors:
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
@@ -66,7 +66,7 @@ engine_settings:
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
- run_id: SnowballTarget1
70
  initialize_from: null
71
  load_model: false
72
  resume: false
 
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
12
+ num_epoch: 80
13
  shared_critic: false
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
 
66
  no_graphics_monitor: false
67
  environment_parameters: null
68
  checkpoint_settings:
69
+ run_id: SnowballTarget2
70
  initialize_from: null
71
  load_model: false
72
  resume: 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 0.087 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)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.746441 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.
@@ -169,7 +166,7 @@ Memory Statistics:
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
@@ -213,10 +210,10 @@ 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]: 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
 
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 0.090 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: 0.745625 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
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 41
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
 
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]: 5125 frames, [64.0 KB-128.0 KB]: 333 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
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
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": {
@@ -26,45 +26,45 @@
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": {
@@ -86,14 +86,14 @@
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
  },
@@ -110,27 +110,27 @@
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": {
@@ -148,67 +148,67 @@
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,
@@ -217,48 +217,48 @@
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
  }
@@ -267,34 +267,34 @@
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
  }
@@ -307,31 +307,31 @@
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
  }
@@ -340,19 +340,19 @@
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
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.8054616451263428,
6
+ "min": 0.7970304489135742,
7
+ "max": 2.796876907348633,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 7655.107421875,
12
+ "min": 7655.107421875,
13
+ "max": 28550.51953125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.283506393432617,
30
+ "min": 0.5775161981582642,
31
+ "max": 13.283506393432617,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2590.28369140625,
36
+ "min": 112.03813934326172,
37
+ "max": 2703.60400390625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.06817431198832985,
42
+ "min": 0.06756688092392778,
43
+ "max": 0.07106685170886042,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.2726972479533194,
48
+ "min": 0.2707678186177525,
49
+ "max": 0.3552740258691832,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.16712515845429154,
54
+ "min": 0.13125464004823537,
55
+ "max": 0.28420236393809317,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.6685006338171662,
60
+ "min": 0.5250185601929415,
61
+ "max": 1.421011819690466,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
  "value": 2.694097306000002e-06,
66
  "min": 2.694097306000002e-06,
67
+ "max": 9.7294002706e-05,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
 
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
  },
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.113636363636363,
114
+ "min": 4.590909090909091,
115
+ "max": 26.113636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1149.0,
120
+ "min": 202.0,
121
+ "max": 1429.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.113636363636363,
126
+ "min": 4.590909090909091,
127
+ "max": 26.113636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1149.0,
132
+ "min": 202.0,
133
+ "max": 1429.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1741888791",
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=SnowballTarget2 --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": "1741891744"
160
  },
161
+ "total": 2952.4862104669996,
162
  "count": 1,
163
+ "self": 0.7480669719993784,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.021806628000376804,
167
  "count": 1,
168
+ "self": 0.021806628000376804
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2951.716336867,
172
  "count": 1,
173
+ "self": 0.4181947549677716,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.9771829509995769,
177
  "count": 1,
178
+ "self": 1.9771829509995769
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2949.177502338032,
182
  "count": 18192,
183
+ "self": 0.42027468496689835,
184
  "children": {
185
  "env_step": {
186
+ "total": 318.98213006004517,
187
  "count": 18192,
188
+ "self": 243.04176356817106,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 75.69720600698656,
192
  "count": 18192,
193
+ "self": 1.3682364289729776,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 74.32896957801358,
197
  "count": 18192,
198
+ "self": 74.32896957801358
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.2431604848875395,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2950.04085903698,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 2737.4613575169233,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.003148694999708823,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0009813129986468994,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.002167382001061924,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.002167382001061924
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.06359044999999242,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0005663920001097722,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004438809996827331,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004438809996827331
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.06072710500029643,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.06072710500029643
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018530719999034773,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00037505399996007327,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001478017999943404,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001478017999943404
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 212.5795015200565,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 9.79515217006292,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.54457634304481,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.54457634304481
280
  },
281
  "communicator.exchange": {
282
+ "total": 164.40729102195473,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 164.40729102195473
286
  },
287
  "steps_from_proto": {
288
+ "total": 32.83248198499405,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 6.024030621067595,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.80845136392645,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 26.80845136392645
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 2629.77509759302,
311
  "count": 18192,
312
+ "self": 0.4979380089944243,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 28.03423390302396,
316
  "count": 18192,
317
+ "self": 27.570013334023315,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.4642205690006449,
321
  "count": 4,
322
+ "self": 0.4642205690006449
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 2601.2429256810015,
328
  "count": 90,
329
+ "self": 1052.9212974659663,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 1548.3216282150352,
333
+ "count": 122320,
334
+ "self": 1548.3216282150352
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.2950004020240158e-06,
344
  "count": 1,
345
+ "self": 1.2950004020240158e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.14345552800023142,
349
  "count": 1,
350
+ "self": 0.001372257000184618,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.1420832710000468,
354
  "count": 1,
355
+ "self": 0.1420832710000468
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -3,57 +3,57 @@
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
  ]
12
  },
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
  ]
21
  },
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
  ]
30
  },
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
  ]
39
  },
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
  ]
48
  }
49
  ],
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
  },
 
3
  "checkpoints": [
4
  {
5
  "steps": 49936,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
7
  "reward": 19.09090909090909,
8
+ "creation_time": 1741889504.9243116,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
  "steps": 99960,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 22.272727272727273,
17
+ "creation_time": 1741890270.800501,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
  "steps": 149984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 25.363636363636363,
26
+ "creation_time": 1741891027.6491692,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
  "steps": 199984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.454545454545453,
35
+ "creation_time": 1741891743.4036508,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
39
  },
40
  {
41
  "steps": 200112,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.454545454545453,
44
+ "creation_time": 1741891743.5653856,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
  "steps": 200112,
52
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
53
+ "reward": 25.454545454545453,
54
+ "creation_time": 1741891743.5653856,
55
  "auxillary_file_paths": [
56
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },