Hugging Face's logo

ByteExplorer
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
ByteExplorer commited on
Commit
74c77d3
·
1 Parent(s): 0c8f2c5

First 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 +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.1689707087.arran.446548.0 +3 -0
  14. config.json +1 -1
  15. configuration.yaml +1 -1
  16. run_logs/Player-0.log +7 -10
  17. run_logs/timers.json +100 -100
  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 sha256:79676eddf333eda0172ab34f0da9ccc3e799c058371f54986603ab507affaacc
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed8780a233370b3b34ac85c741a2552de83284eca68e5d8e3a0600f308b8c77
3
  size 646532
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d420092fd00c76372eb06f9aca52eea50dc39064035b606f50b8b55d011978eb
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259e105e972a97bd113c4bd64f748f1f4a9e055ebafd681ad59c7f15ca855ae0
3
  size 646532
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d27ed209ec6b4f92ee737bd9f06572d23972fb79ab5efd3a348d406c0beabbf5
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9952af9673cc28630c6f9cdda98b716dbfe451d46e1af421036825f5f37130
3
+ size 3843968
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79676eddf333eda0172ab34f0da9ccc3e799c058371f54986603ab507affaacc
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed8780a233370b3b34ac85c741a2552de83284eca68e5d8e3a0600f308b8c77
3
  size 646532
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406ee0a0e418ce5a30e04522e734cddf1d3475d0e449b2e541558a8328434f6b
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8cf73cbebc56ed147edcd5dd006d667a98f3d92af138458cc261d9274cdcc11
3
+ size 3843968
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79676eddf333eda0172ab34f0da9ccc3e799c058371f54986603ab507affaacc
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed8780a233370b3b34ac85c741a2552de83284eca68e5d8e3a0600f308b8c77
3
  size 646532
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c842ab6e877644f108eef42479bc310393c619134042f2d62536a195a3e828e
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a850cf4b4678ffeae40a1adf3cb5a0d05640979fa85ae13fa47cf8b92585f46
3
+ size 3843968
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6cd3425631bbceaa3b999830c00edf57be02a17005e61ef7c1fb39547c9d794
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48be60b6801a78ebf07bbf85eb264560110bce0c8fe04c5189d4d6d65ba269b
3
  size 646532
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c511238286fe06cef79fea302135a650838857f1c32d81449edc82df3f7ef66
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb08b4fe44f2fb858ca88c4b033679ceb50dbca78ad0bf8723b8125bbbb261e
3
+ size 3843968
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2489747cba812caa2097210e04fa841ae6214d894b51450cd02753cab70b0e75
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f565dfe424680c98da2454b1426d9a1a10e97b38d1fc4313e229b46c338029f
3
  size 646532
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edfc1db05b92b5d6350cbc8f070eb3e96968f7f2a17603f7be38e543908fb46f
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2959111ecf1be0ccb8fdd146826a45ae04fbfe64fa2ea14fe9f4527ec14d09c
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c842ab6e877644f108eef42479bc310393c619134042f2d62536a195a3e828e
3
- size 3843200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a850cf4b4678ffeae40a1adf3cb5a0d05640979fa85ae13fa47cf8b92585f46
3
+ size 3843968
SnowballTarget/events.out.tfevents.1689707087.arran.446548.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cadaa1de14f631283771eeb98c08c23e4f177a9ad237e136165892efb12cfb15
3
+ size 28459
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -68,7 +68,7 @@ checkpoint_settings:
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
- force: false
72
  train_model: false
73
  inference: false
74
  results_dir: results
 
68
  initialize_from: null
69
  load_model: false
70
  resume: false
71
+ force: true
72
  train_model: false
73
  inference: false
74
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/home/arran/huggingface/RL-U5/ml-agents/training-envs-executable
2
  Mono config path = '/home/arran/huggingface/RL-U5/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: /home/arran/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /home/arran/.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 /home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -14,7 +11,7 @@ NullGfxDevice:
14
  Renderer: Null Device
15
  Vendor: Unity Technologies
16
  Begin MonoManager ReloadAssembly
17
- - Completed reload, in 0.044 seconds
18
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
19
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
20
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -25,7 +22,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
25
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
26
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
27
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
28
- UnloadTime: 0.389431 ms
29
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
30
  requesting resize 84 x 84
31
  Setting up 8 worker threads for Enlighten.
@@ -219,7 +216,7 @@ Memory Statistics:
219
  Peak Allocated Bytes 0 B
220
  Overflow Count 0
221
  [ALLOC_DEFAULT] Dual Thread Allocator
222
- Peak main deferred allocation count 36
223
  [ALLOC_BUCKET]
224
  Large Block size 4.0 MB
225
  Used Block count 1
@@ -228,13 +225,13 @@ Memory Statistics:
228
  Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
229
  Requested Block Size 16.0 MB
230
  Peak Block count 1
231
- Peak Allocated memory 6.9 MB
232
  Peak Large allocation bytes 0 B
233
  [ALLOC_DEFAULT_THREAD]
234
  Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
235
  Requested Block Size 16.0 MB
236
  Peak Block count 1
237
- Peak Allocated memory 17.4 MB
238
  Peak Large allocation bytes 16.0 MB
239
  [ALLOC_TEMP_JOB_1_FRAME]
240
  Initial Block Size 2.0 MB
@@ -263,10 +260,10 @@ Memory Statistics:
263
  Used Block count 1
264
  Peak Allocated bytes 1.0 MB
265
  [ALLOC_GFX_MAIN]
266
- Peak usage frame count: [32.0 KB-64.0 KB]: 4903 frames, [64.0 KB-128.0 KB]: 560 frames
267
  Requested Block Size 16.0 MB
268
  Peak Block count 1
269
- Peak Allocated memory 66.4 KB
270
  Peak Large allocation bytes 0 B
271
  [ALLOC_GFX_THREAD]
272
  Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
 
2
  Mono config path = '/home/arran/huggingface/RL-U5/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 /home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
11
  Renderer: Null Device
12
  Vendor: Unity Technologies
13
  Begin MonoManager ReloadAssembly
14
+ - Completed reload, in 0.043 seconds
15
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
16
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
17
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
22
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
23
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
24
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
25
+ UnloadTime: 0.395432 ms
26
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
27
  requesting resize 84 x 84
28
  Setting up 8 worker threads for Enlighten.
 
216
  Peak Allocated Bytes 0 B
217
  Overflow Count 0
218
  [ALLOC_DEFAULT] Dual Thread Allocator
219
+ Peak main deferred allocation count 40
220
  [ALLOC_BUCKET]
221
  Large Block size 4.0 MB
222
  Used Block count 1
 
225
  Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
226
  Requested Block Size 16.0 MB
227
  Peak Block count 1
228
+ Peak Allocated memory 7.0 MB
229
  Peak Large allocation bytes 0 B
230
  [ALLOC_DEFAULT_THREAD]
231
  Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
232
  Requested Block Size 16.0 MB
233
  Peak Block count 1
234
+ Peak Allocated memory 17.5 MB
235
  Peak Large allocation bytes 16.0 MB
236
  [ALLOC_TEMP_JOB_1_FRAME]
237
  Initial Block Size 2.0 MB
 
260
  Used Block count 1
261
  Peak Allocated bytes 1.0 MB
262
  [ALLOC_GFX_MAIN]
263
+ Peak usage frame count: [32.0 KB-64.0 KB]: 4434 frames, [64.0 KB-128.0 KB]: 1029 frames
264
  Requested Block Size 16.0 MB
265
  Peak Block count 1
266
+ Peak Allocated memory 66.8 KB
267
  Peak Large allocation bytes 0 B
268
  [ALLOC_GFX_THREAD]
269
  Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.009873390197754,
6
- "min": 1.0039869546890259,
7
- "max": 2.875833034515381,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9686.705078125,
12
- "min": 9686.705078125,
13
- "max": 29641.2109375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.681685447692871,
30
- "min": 0.3597606420516968,
31
- "max": 12.681685447692871,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2472.9287109375,
36
- "min": 69.79356384277344,
37
- "max": 2570.545166015625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,27 +50,27 @@
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07225372470394872,
54
- "min": 0.06214879379652249,
55
- "max": 0.07483702620386383,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2890148988157949,
60
- "min": 0.24859517518608995,
61
- "max": 0.37418513101931916,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.21148619223751275,
66
- "min": 0.11406359147033929,
67
- "max": 0.26874129335377733,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.845944768950051,
72
- "min": 0.45625436588135715,
73
- "max": 1.3256210822100734,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 25.113636363636363,
114
- "min": 3.1136363636363638,
115
- "max": 25.113636363636363,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1105.0,
120
- "min": 137.0,
121
- "max": 1375.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 25.113636363636363,
126
- "min": 3.1136363636363638,
127
- "max": 25.113636363636363,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1105.0,
132
- "min": 137.0,
133
- "max": 1375.0,
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": "1689560634",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
153
- "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
- "end_time_seconds": "1689560798"
160
  },
161
- "total": 163.34209756800556,
162
  "count": 1,
163
- "self": 0.16737529700913,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.008849259997077752,
167
  "count": 1,
168
- "self": 0.008849259997077752
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 163.16587301099935,
172
  "count": 1,
173
- "self": 0.2459106373062241,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 0.34805920100188814,
177
  "count": 1,
178
- "self": 0.34805920100188814
179
  },
180
  "TrainerController.advance": {
181
- "total": 162.51085895268625,
182
  "count": 18209,
183
- "self": 0.11385590480495011,
184
  "children": {
185
  "env_step": {
186
- "total": 162.3970030478813,
187
  "count": 18209,
188
- "self": 128.49324068587157,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 33.78237352268479,
192
  "count": 18209,
193
- "self": 0.693329913650814,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 33.08904360903398,
197
  "count": 18209,
198
- "self": 33.08904360903398
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.12138883932493627,
204
  "count": 18209,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 162.86546743427607,
209
  "count": 18209,
210
  "is_parallel": true,
211
- "self": 80.8792929445408,
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": 0.0011201209999853745,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.00031727200257591903,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0008028489974094555,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0008028489974094555
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.013202916001318954,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.00021208200632827356,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00013177999790059403,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00013177999790059403
244
  },
245
  "communicator.exchange": {
246
- "total": 0.012136475997976959,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.012136475997976959
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0007225779991131276,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00015818099200259894,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0005643970071105286,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0005643970071105286
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 81.98617448973528,
271
  "count": 18208,
272
  "is_parallel": true,
273
- "self": 3.7775379178929143,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 2.080694572228822,
277
  "count": 18208,
278
  "is_parallel": true,
279
- "self": 2.080694572228822
280
  },
281
  "communicator.exchange": {
282
- "total": 64.41326121330349,
283
  "count": 18208,
284
  "is_parallel": true,
285
- "self": 64.41326121330349
286
  },
287
  "steps_from_proto": {
288
- "total": 11.714680786310055,
289
  "count": 18208,
290
  "is_parallel": true,
291
- "self": 2.2427786746557103,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 9.471902111654344,
295
  "count": 182080,
296
  "is_parallel": true,
297
- "self": 9.471902111654344
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 9.456900443183258e-05,
313
  "count": 1,
314
- "self": 9.456900443183258e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 162.43629478729417,
324
- "count": 84973,
325
  "is_parallel": true,
326
- "self": 0.7586252245018841,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 85.66978424775152,
330
- "count": 84973,
331
  "is_parallel": true,
332
- "self": 85.26204654275352,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.40773770499799866,
336
  "count": 4,
337
  "is_parallel": true,
338
- "self": 0.40773770499799866
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 76.00788531504077,
344
  "count": 90,
345
  "is_parallel": true,
346
- "self": 25.408237125884625,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 50.59964818915614,
350
  "count": 4587,
351
  "is_parallel": true,
352
- "self": 50.59964818915614
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.060949651000555605,
364
  "count": 1,
365
- "self": 0.0004994760020053945,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.06045017499855021,
369
  "count": 1,
370
- "self": 0.06045017499855021
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.9890428781509399,
6
+ "min": 0.9692286849021912,
7
+ "max": 2.8643295764923096,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 9508.658203125,
12
+ "min": 9508.658203125,
13
+ "max": 29459.62890625,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.041976928710938,
30
+ "min": 0.312862366437912,
31
+ "max": 12.041976928710938,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2348.185546875,
36
+ "min": 60.69529724121094,
37
+ "max": 2421.79296875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06905941159764588,
54
+ "min": 0.0637184276286765,
55
+ "max": 0.07654857261051945,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.2762376463905835,
60
+ "min": 0.254873710514706,
61
+ "max": 0.36285360355395824,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.21753805594555303,
66
+ "min": 0.10302229644274158,
67
+ "max": 0.27242677831182294,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8701522237822121,
72
+ "min": 0.4120891857709663,
73
+ "max": 1.3621338915591146,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 23.863636363636363,
114
+ "min": 2.9318181818181817,
115
+ "max": 23.977272727272727,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1050.0,
120
+ "min": 129.0,
121
+ "max": 1299.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 23.863636363636363,
126
+ "min": 2.9318181818181817,
127
+ "max": 23.977272727272727,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1050.0,
132
+ "min": 129.0,
133
+ "max": 1299.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1689707086",
152
  "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
153
+ "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "0.31.0.dev0",
155
  "mlagents_envs_version": "0.31.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.11.0+cu102",
158
  "numpy_version": "1.21.2",
159
+ "end_time_seconds": "1689707271"
160
  },
161
+ "total": 184.54512175401032,
162
  "count": 1,
163
+ "self": 0.21794814300665166,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.009685946002718993,
167
  "count": 1,
168
+ "self": 0.009685946002718993
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 184.31748766500095,
172
  "count": 1,
173
+ "self": 0.2535555436188588,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 2.474105157001759,
177
  "count": 1,
178
+ "self": 2.474105157001759
179
  },
180
  "TrainerController.advance": {
181
+ "total": 181.51562136938446,
182
  "count": 18209,
183
+ "self": 0.12030773251899518,
184
  "children": {
185
  "env_step": {
186
+ "total": 181.39531363686547,
187
  "count": 18209,
188
+ "self": 131.65605812524154,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 49.61544951298856,
192
  "count": 18209,
193
+ "self": 0.7191228498268174,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 48.896326663161744,
197
  "count": 18209,
198
+ "self": 48.896326663161744
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.1238059986353619,
204
  "count": 18209,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 183.9796360952314,
209
  "count": 18209,
210
  "is_parallel": true,
211
+ "self": 98.11927624826785,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0012240060023032129,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.00048465700820088387,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.000739348994102329,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.000739348994102329
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.013724046002607793,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.00021589899552054703,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0001663450093474239,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0001663450093474239
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.012626758994883858,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.012626758994883858
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.000715043002855964,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00015529400843661278,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0005597489944193512,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0005597489944193512
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 85.86035984696355,
271
  "count": 18208,
272
  "is_parallel": true,
273
+ "self": 3.9446354413666995,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 2.196138688828796,
277
  "count": 18208,
278
  "is_parallel": true,
279
+ "self": 2.196138688828796
280
  },
281
  "communicator.exchange": {
282
+ "total": 67.31191313015006,
283
  "count": 18208,
284
  "is_parallel": true,
285
+ "self": 67.31191313015006
286
  },
287
  "steps_from_proto": {
288
+ "total": 12.407672586617991,
289
  "count": 18208,
290
  "is_parallel": true,
291
+ "self": 2.4541078687179834,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 9.953564717900008,
295
  "count": 182080,
296
  "is_parallel": true,
297
+ "self": 9.953564717900008
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 6.88599975546822e-05,
313
  "count": 1,
314
+ "self": 6.88599975546822e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 181.3120569051389,
324
+ "count": 129760,
325
  "is_parallel": true,
326
+ "self": 1.0343860988214146,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 96.94700801130966,
330
+ "count": 129760,
331
  "is_parallel": true,
332
+ "self": 96.50593304431823,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 0.44107496699143667,
336
  "count": 4,
337
  "is_parallel": true,
338
+ "self": 0.44107496699143667
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 83.33066279500781,
344
  "count": 90,
345
  "is_parallel": true,
346
+ "self": 25.919892322315718,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 57.41077047269209,
350
  "count": 4587,
351
  "is_parallel": true,
352
+ "self": 57.41077047269209
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.0741367349983193,
364
  "count": 1,
365
+ "self": 0.0007672310021007434,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.07336950399621855,
369
  "count": 1,
370
+ "self": 0.07336950399621855
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -4,8 +4,8 @@
4
  {
5
  "steps": 49936,
6
  "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.636363636363637,
8
- "creation_time": 1689560675.426922,
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": 20.636363636363637,
17
- "creation_time": 1689560716.4807212,
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": 23.90909090909091,
26
- "creation_time": 1689560757.8209734,
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": 25.454545454545453,
35
- "creation_time": 1689560798.0661182,
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": 25.454545454545453,
44
- "creation_time": 1689560798.1378164,
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": 25.454545454545453,
54
- "creation_time": 1689560798.1378164,
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": 13.909090909090908,
8
+ "creation_time": 1689707133.4070015,
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": 20.09090909090909,
17
+ "creation_time": 1689707178.0124168,
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": 22.636363636363637,
26
+ "creation_time": 1689707223.1507776,
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": 23.818181818181817,
35
+ "creation_time": 1689707271.032672,
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": 23.818181818181817,
44
+ "creation_time": 1689707271.1188424,
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": 23.818181818181817,
54
+ "creation_time": 1689707271.1188424,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]