Hugging Face's logo

Aris1129
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
 Metrics Community
Aris1129 commited on
Commit
7772d8e
·
verified ·
1 Parent(s): 7f37aa1

Snowball

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-149984.onnx +1 -1
  3. SnowballTarget/SnowballTarget-149984.pt +2 -2
  4. SnowballTarget/SnowballTarget-199984.onnx +1 -1
  5. SnowballTarget/SnowballTarget-199984.pt +2 -2
  6. SnowballTarget/SnowballTarget-200112.onnx +1 -1
  7. SnowballTarget/SnowballTarget-200112.pt +2 -2
  8. SnowballTarget/SnowballTarget-49936.onnx +1 -1
  9. SnowballTarget/SnowballTarget-49936.pt +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +1 -1
  11. SnowballTarget/SnowballTarget-99960.pt +2 -2
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/events.out.tfevents.1779887936.9218a57992ed.6757.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +7 -7
  17. run_logs/timers.json +103 -103
  18. run_logs/training_status.json +12 -12
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ab9680bebc783e4306e075e89eb016afa16d79956280bbb21758c773f3b324
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613eadf303974b3c82751c880592d6e14d11fb0e6afd415e9a720d414d1e055a
3
  size 650646
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:599080557c70e6dcb3b841d1c953befa1365abd3c9407ceb774077574804c4da
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d1c6a09024bbd7e895e7d3fd4f4aaa0043ffe3520007050d78a314f2db500b
3
  size 650646
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0410f6d0bfb67d771ef327ff12928972e5d2132c0b162961690dcf9336651cc7
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa127a0f5a3bb5affbc113dbd44c49dba03181f8798bfa48f5f462f5ee55d743
3
+ size 3848942
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ab9680bebc783e4306e075e89eb016afa16d79956280bbb21758c773f3b324
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613eadf303974b3c82751c880592d6e14d11fb0e6afd415e9a720d414d1e055a
3
  size 650646
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c77d2a60e35bd37b6f8b078dc5f5cdefb5b045d7c618a31e2dcc5d7dc86bb18e
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f85ca1d0ecf880c2bb181d789cd0db03d5a23b6a315b9cae768b4b2fa57489
3
+ size 3848942
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ab9680bebc783e4306e075e89eb016afa16d79956280bbb21758c773f3b324
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613eadf303974b3c82751c880592d6e14d11fb0e6afd415e9a720d414d1e055a
3
  size 650646
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4495ead9dc49b9dbdc5c1c6f749ffeecd63ad09b0986f4100624c458d2cde0e6
3
- size 3849902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439a8073afcb3f5e025bb1527c572d165eba96dee274de86a0f194369f4e0585
3
+ size 3848942
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a88db3f4e33b99a8527e3810c667b69cc19db18d875826aeec95aaea8a9911f
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5016914e0653104f8174f1382530b751ee0cf195c7bac1323613be1b65bcb517
3
  size 650646
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6def2a588a0dd98ba0a0cf6a16149699b3811b000b3d2f287611f36bd5976675
3
- size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5f5e650eeb46024b28e603b822fa94aef0eb8da17bd80126dee17891d3bdf0
3
+ size 3848867
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25561a16015f619aa0b120fcb43e95cfce222cb74dc9da46275bdc21a13e976c
3
  size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8627554d0a005f729999fdb71e21129b06532666697baff671477db017861485
3
  size 650646
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1eb79ae6cd7b767ca8ffd5d1d8b6d681abf87135e6cb048080d34bedc83181e
3
- size 3849827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95f9685d57420eded49629bd628860a38fdc0f556acf692ab9a85d4b94e9e58
3
+ size 3848867
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c67f58a3f361c249c0d6d441c36fa94bb5d57e9b3a8b030a36ae59b2b34ed13
3
- size 3849077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02db51b329aed452016a3e7806ddb5ef3fd37fa3c7d050d617f196f0ae81252d
3
+ size 3848117
SnowballTarget/events.out.tfevents.1779887936.9218a57992ed.6757.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec2b01a56542ea8f23c878532c89f7cdae2a4ac6184b977042c3c3b6110ae76
3
+ size 33060
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 64, "buffer_size": 2048, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": 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": 64, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": 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
@@ -5,7 +5,7 @@ behaviors:
5
  hyperparameters:
6
  batch_size: 64
7
  buffer_size: 2048
8
- learning_rate: 0.0002
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
 
5
  hyperparameters:
6
  batch_size: 64
7
  buffer_size: 2048
8
+ learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
11
  lambd: 0.95
run_logs/Player-0.log CHANGED
@@ -34,7 +34,7 @@ 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 0.093 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 +45,7 @@ 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: 0.691065 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 +169,7 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 46
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
@@ -178,13 +178,13 @@ Memory Statistics:
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 7.1 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 17.3 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,10 +213,10 @@ 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]: 4607 frames, [64.0 KB-128.0 KB]: 851 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.7 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
 
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 0.104 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: 0.871762 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 40
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
 
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 6.6 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
 
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]: 5115 frames, [64.0 KB-128.0 KB]: 343 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
+ Peak Allocated memory 66.8 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
  Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9784275889396667,
6
- "min": 0.9784275889396667,
7
- "max": 2.855565071105957,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9298.9755859375,
12
- "min": 9298.9755859375,
13
- "max": 29149.609375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,51 +26,51 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.783576011657715,
30
- "min": 0.4029771387577057,
31
- "max": 12.783576011657715,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2492.79736328125,
36
- "min": 78.17756652832031,
37
- "max": 2573.56982421875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
- "value": 0.09589547802789086,
42
- "min": 0.09358842293172617,
43
- "max": 0.10411659102982787,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
- "value": 0.38358191211156345,
48
- "min": 0.381160352376801,
49
- "max": 0.5205829551491393,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
- "value": 0.19614630497480726,
54
- "min": 0.13167814352448345,
55
- "max": 0.27417958275798493,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
- "value": 0.784585219899229,
60
- "min": 0.5267125740979338,
61
- "max": 1.322642925031045,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
- "value": 5.388097306000005e-06,
66
- "min": 5.388097306000005e-06,
67
- "max": 0.00019458800270600002,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
- "value": 2.155238922400002e-05,
72
- "min": 2.155238922400002e-05,
73
- "max": 0.00092344003828,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.886363636363637,
114
- "min": 3.9318181818181817,
115
- "max": 25.886363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1139.0,
120
- "min": 173.0,
121
- "max": 1356.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.886363636363637,
126
- "min": 3.9318181818181817,
127
- "max": 25.886363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1139.0,
132
- "min": 173.0,
133
- "max": 1356.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,7 +148,7 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1779871776",
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",
@@ -156,59 +156,59 @@
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1779872300"
160
  },
161
- "total": 524.254667187,
162
  "count": 1,
163
- "self": 0.4327090599999792,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.025732504000075096,
167
  "count": 1,
168
- "self": 0.025732504000075096
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 523.7962256229999,
172
  "count": 1,
173
- "self": 0.39671435300340363,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 2.9052340890000323,
177
  "count": 1,
178
- "self": 2.9052340890000323
179
  },
180
  "TrainerController.advance": {
181
- "total": 520.3985415089967,
182
  "count": 18192,
183
- "self": 0.3951922029823436,
184
  "children": {
185
  "env_step": {
186
- "total": 343.6476346530021,
187
  "count": 18192,
188
- "self": 269.9591755849808,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 73.4544331310102,
192
  "count": 18192,
193
- "self": 1.3224016870052537,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 72.13203144400495,
197
  "count": 18192,
198
- "self": 72.13203144400495
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.23402593701109708,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 522.0082425279918,
209
  "count": 18192,
210
  "is_parallel": true,
211
- "self": 284.9970220359926,
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": 0.0054088310000679485,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0038474890001225504,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0015613419999453981,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0015613419999453981
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03974832900007641,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0005937430000813038,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0004279170000245358,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0004279170000245358
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03678482200007238,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03678482200007238
250
  },
251
  "steps_from_proto": {
252
- "total": 0.001941846999898189,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.000385950999771012,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.001555896000127177,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.001555896000127177
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 237.0112204919992,
271
  "count": 18191,
272
  "is_parallel": true,
273
- "self": 10.856685434028122,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.8941139669902896,
277
  "count": 18191,
278
  "is_parallel": true,
279
- "self": 5.8941139669902896
280
  },
281
  "communicator.exchange": {
282
- "total": 181.06189973399887,
283
  "count": 18191,
284
  "is_parallel": true,
285
- "self": 181.06189973399887
286
  },
287
  "steps_from_proto": {
288
- "total": 39.19852135698193,
289
  "count": 18191,
290
  "is_parallel": true,
291
- "self": 7.010774281977206,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 32.18774707500472,
295
  "count": 181910,
296
  "is_parallel": true,
297
- "self": 32.18774707500472
298
  }
299
  }
300
  }
@@ -307,31 +307,31 @@
307
  }
308
  },
309
  "trainer_advance": {
310
- "total": 176.35571465301223,
311
  "count": 18192,
312
- "self": 0.4739027969922063,
313
  "children": {
314
  "process_trajectory": {
315
- "total": 27.887092832020357,
316
  "count": 18192,
317
- "self": 27.385612156020557,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
- "total": 0.501480675999801,
321
  "count": 4,
322
- "self": 0.501480675999801
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
- "total": 147.99471902399966,
328
  "count": 90,
329
- "self": 40.63004318900141,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
- "total": 107.36467583499825,
333
  "count": 9177,
334
- "self": 107.36467583499825
335
  }
336
  }
337
  }
@@ -340,19 +340,19 @@
340
  }
341
  },
342
  "trainer_threads": {
343
- "total": 1.478999820392346e-06,
344
  "count": 1,
345
- "self": 1.478999820392346e-06
346
  },
347
  "TrainerController._save_models": {
348
- "total": 0.09573419299999841,
349
  "count": 1,
350
- "self": 0.0008157709999068175,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
- "total": 0.0949184220000916,
354
  "count": 1,
355
- "self": 0.0949184220000916
356
  }
357
  }
358
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9082087874412537,
6
+ "min": 0.9060767889022827,
7
+ "max": 2.8676702976226807,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 8631.6162109375,
12
+ "min": 8631.6162109375,
13
+ "max": 29273.177734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.24351692199707,
30
+ "min": 0.28583642840385437,
31
+ "max": 13.24351692199707,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2582.48583984375,
36
+ "min": 55.452266693115234,
37
+ "max": 2690.825439453125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Losses.PolicyLoss.mean": {
41
+ "value": 0.09316941940778634,
42
+ "min": 0.09316941940778634,
43
+ "max": 0.10633131119099619,
44
  "count": 20
45
  },
46
  "SnowballTarget.Losses.PolicyLoss.sum": {
47
+ "value": 0.37267767763114534,
48
+ "min": 0.37267767763114534,
49
+ "max": 0.531656555954981,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.ValueLoss.mean": {
53
+ "value": 0.1796282591736492,
54
+ "min": 0.1099558026328975,
55
+ "max": 0.28154423504191284,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.ValueLoss.sum": {
59
+ "value": 0.7185130366945968,
60
+ "min": 0.43982321053159,
61
+ "max": 1.3127186440807932,
62
  "count": 20
63
  },
64
  "SnowballTarget.Policy.LearningRate.mean": {
65
+ "value": 8.082097306000007e-06,
66
+ "min": 8.082097306000007e-06,
67
+ "max": 0.000291882002706,
68
  "count": 20
69
  },
70
  "SnowballTarget.Policy.LearningRate.sum": {
71
+ "value": 3.232838922400003e-05,
72
+ "min": 3.232838922400003e-05,
73
+ "max": 0.00138516003828,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.Epsilon.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.386363636363637,
114
+ "min": 3.1136363636363638,
115
+ "max": 26.386363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1161.0,
120
+ "min": 137.0,
121
+ "max": 1428.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.386363636363637,
126
+ "min": 3.1136363636363638,
127
+ "max": 26.386363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1161.0,
132
+ "min": 137.0,
133
+ "max": 1428.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1779887935",
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",
 
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.8.0+cu128",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1779888585"
160
  },
161
+ "total": 649.9418392939999,
162
  "count": 1,
163
+ "self": 0.5905147009998473,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.03183859700016001,
167
  "count": 1,
168
+ "self": 0.03183859700016001
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 649.3194859959999,
172
  "count": 1,
173
+ "self": 0.5921733039901937,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.1773203049999665,
177
  "count": 1,
178
+ "self": 3.1773203049999665
179
  },
180
  "TrainerController.advance": {
181
+ "total": 645.4794628240097,
182
  "count": 18192,
183
+ "self": 0.6732999559849304,
184
  "children": {
185
  "env_step": {
186
+ "total": 423.2551363460118,
187
  "count": 18192,
188
+ "self": 367.0260468249762,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 55.85102293500995,
192
  "count": 18192,
193
+ "self": 2.050922412998034,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 53.80010052201192,
197
  "count": 18192,
198
+ "self": 53.80010052201192
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.37806658602562493,
204
  "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 646.3108106909863,
209
  "count": 18192,
210
  "is_parallel": true,
211
+ "self": 328.5624920850023,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.005516879999959201,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.003967527999975573,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.001549351999983628,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.001549351999983628
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0428268929999831,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000722821999943335,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004796560001523176,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004796560001523176
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.039400070999818126,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.039400070999818126
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0022243440000693226,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0004206309999972291,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0018037130000720936,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0018037130000720936
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 317.74831860598397,
271
  "count": 18191,
272
  "is_parallel": true,
273
+ "self": 14.563851238035795,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 7.7084965579754225,
277
  "count": 18191,
278
  "is_parallel": true,
279
+ "self": 7.7084965579754225
280
  },
281
  "communicator.exchange": {
282
+ "total": 246.22839854299673,
283
  "count": 18191,
284
  "is_parallel": true,
285
+ "self": 246.22839854299673
286
  },
287
  "steps_from_proto": {
288
+ "total": 49.24757226697602,
289
  "count": 18191,
290
  "is_parallel": true,
291
+ "self": 8.704771586964625,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 40.542800680011396,
295
  "count": 181910,
296
  "is_parallel": true,
297
+ "self": 40.542800680011396
298
  }
299
  }
300
  }
 
307
  }
308
  },
309
  "trainer_advance": {
310
+ "total": 221.551026522013,
311
  "count": 18192,
312
+ "self": 0.864402156023516,
313
  "children": {
314
  "process_trajectory": {
315
+ "total": 31.15272031799077,
316
  "count": 18192,
317
+ "self": 30.767629106990626,
318
  "children": {
319
  "RLTrainer._checkpoint": {
320
+ "total": 0.38509121100014454,
321
  "count": 4,
322
+ "self": 0.38509121100014454
323
  }
324
  }
325
  },
326
  "_update_policy": {
327
+ "total": 189.5339040479987,
328
  "count": 90,
329
+ "self": 49.68910326499122,
330
  "children": {
331
  "TorchPPOOptimizer.update": {
332
+ "total": 139.84480078300749,
333
  "count": 9177,
334
+ "self": 139.84480078300749
335
  }
336
  }
337
  }
 
340
  }
341
  },
342
  "trainer_threads": {
343
+ "total": 1.032999989547534e-06,
344
  "count": 1,
345
+ "self": 1.032999989547534e-06
346
  },
347
  "TrainerController._save_models": {
348
+ "total": 0.07052853000004689,
349
  "count": 1,
350
+ "self": 0.0008835759999783477,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.06964495400006854,
354
  "count": 1,
355
+ "self": 0.06964495400006854
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 14.636363636363637,
8
- "creation_time": 1779871911.628292,
9
  "auxillary_file_paths": [
10
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
@@ -13,8 +13,8 @@
13
  {
14
  "steps": 99960,
15
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 20.181818181818183,
17
- "creation_time": 1779872042.3997688,
18
  "auxillary_file_paths": [
19
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
@@ -22,8 +22,8 @@
22
  {
23
  "steps": 149984,
24
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 24.545454545454547,
26
- "creation_time": 1779872171.9790745,
27
  "auxillary_file_paths": [
28
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
@@ -31,8 +31,8 @@
31
  {
32
  "steps": 199984,
33
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 26.545454545454547,
35
- "creation_time": 1779872300.2267184,
36
  "auxillary_file_paths": [
37
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
  ]
@@ -40,8 +40,8 @@
40
  {
41
  "steps": 200112,
42
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 26.545454545454547,
44
- "creation_time": 1779872300.3433077,
45
  "auxillary_file_paths": [
46
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
@@ -50,8 +50,8 @@
50
  "final_checkpoint": {
51
  "steps": 200112,
52
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 26.545454545454547,
54
- "creation_time": 1779872300.3433077,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
 
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.909090909090908,
8
+ "creation_time": 1779888096.3764153,
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": 25.181818181818183,
17
+ "creation_time": 1779888258.7359755,
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": 25.0,
26
+ "creation_time": 1779888421.4086268,
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": 27.181818181818183,
35
+ "creation_time": 1779888584.5442815,
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": 27.181818181818183,
44
+ "creation_time": 1779888584.6279478,
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": 27.181818181818183,
54
+ "creation_time": 1779888584.6279478,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]