Hugging Face's logo

ammr
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
unity-ml-agents
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
ammr commited on
Commit
efceb3b
·
1 Parent(s): 92f7f98

addsnowballtarget

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.1678034901.8cac745c4078.2553.0 → events.out.tfevents.1678035795.8cac745c4078.6559.0} +2 -2
  14. config.json +1 -1
  15. configuration.yaml +2 -2
  16. run_logs/Player-0.log +14 -17
  17. run_logs/timers.json +123 -123
  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 sha256:7688d35c2dc6fabec5fa481d56b6f4a4d4713593cd09e2979228a30555cc02fa
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a211d604995ede8e5eb3cb3dc9eca2fc377a51dc8c7a0bec2dac53dbde9ba7ea
3
  size 645119
SnowballTarget/SnowballTarget-149984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54d10f6e4d97876a949f61936c87067e42e6dbcc3519e8923e0add06d781b87c
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b03b4504c8ed32c0533476fa9f10339f51d93753a89ecec00350dbbb0ae94c
3
  size 645119
SnowballTarget/SnowballTarget-149984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d16ba23efccce3105b9ae99fd14991d851e67afb031802a507a00e256233480
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6863ee3eb2886586a35d004afdadfe2e8f95d41a994016fac30da9a4c8b2303
3
+ size 3845582
SnowballTarget/SnowballTarget-199984.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7688d35c2dc6fabec5fa481d56b6f4a4d4713593cd09e2979228a30555cc02fa
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a211d604995ede8e5eb3cb3dc9eca2fc377a51dc8c7a0bec2dac53dbde9ba7ea
3
  size 645119
SnowballTarget/SnowballTarget-199984.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:921e326b221b147dc85de42abbead1b3f03d7dd36e2c2aff25ac4ad430a33605
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fee661f793dde6360db1caf33a80112d384cc65fa399cdac6263bf126eed5e9
3
+ size 3845582
SnowballTarget/SnowballTarget-200112.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7688d35c2dc6fabec5fa481d56b6f4a4d4713593cd09e2979228a30555cc02fa
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a211d604995ede8e5eb3cb3dc9eca2fc377a51dc8c7a0bec2dac53dbde9ba7ea
3
  size 645119
SnowballTarget/SnowballTarget-200112.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e6f8fce3dae6b9d1dd3039c6b6c099e522368853231d080a37ff2fdd388de8e
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ad410d79b14e251b5abbac09fcb4481d8f3b610854dbccaa6469f3d8157ece
3
+ size 3845582
SnowballTarget/SnowballTarget-49936.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a52d2705ada8fbcb9f2b2355542276b1bd047bab31eeeae793e4a63b4ba325d
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed1406acad3dda42b20ecfedd83635034b8bf20d4250df62f88912f36b30b0f
3
  size 645119
SnowballTarget/SnowballTarget-49936.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:191e78985f7b61cb795b71c0391ce9ae9add0efd582c111c5d716072d45c4a72
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5eb4d22c768e920ebfcdef67356d281fdde2d3596dbbe42e2cfda20f2adbfe
3
+ size 3845582
SnowballTarget/SnowballTarget-99960.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:078d8d4345a97fe7b6f043a3362303a15646741ea2469c5ca21c52d807ae5146
3
  size 645119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0cced6ea41fcd181a20bdbcc43f2277106036f9664f7f2a88b928dcd800adb
3
  size 645119
SnowballTarget/SnowballTarget-99960.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a4d297d3c2bb4955e09e74d8f0c90b44f9239fe456d4e1dcc86b154b85c79a0
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf3fa39891ac28aa9860325dae393a45d4031e9a831f3357bac86d51d3329cb
3
+ size 3845582
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e6f8fce3dae6b9d1dd3039c6b6c099e522368853231d080a37ff2fdd388de8e
3
- size 3845585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ad410d79b14e251b5abbac09fcb4481d8f3b610854dbccaa6469f3d8157ece
3
+ size 3845582
SnowballTarget/{events.out.tfevents.1678034901.8cac745c4078.2553.0 → events.out.tfevents.1678035795.8cac745c4078.6559.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e21d3a97625d99e4366a384caa1cfde2fd7d6edb803a0954d5a71964ce5272
3
- size 39554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433036b92a5b8a3bbfb9ee98dcd635b00d3f6a6cd8bb47de3c1823f6ca0a9843
3
+ size 24633
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": 0.1, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "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": 0.0001, "beta": 0.005, "epsilon": 0.1, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "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
@@ -9,7 +9,7 @@ behaviors:
9
  beta: 0.005
10
  epsilon: 0.1
11
  lambd: 0.95
12
- num_epoch: 3
13
  learning_rate_schedule: linear
14
  beta_schedule: linear
15
  epsilon_schedule: linear
@@ -66,7 +66,7 @@ checkpoint_settings:
66
  initialize_from: null
67
  load_model: false
68
  resume: false
69
- force: false
70
  train_model: false
71
  inference: false
72
  results_dir: results
 
9
  beta: 0.005
10
  epsilon: 0.1
11
  lambd: 0.95
12
+ num_epoch: 5
13
  learning_rate_schedule: linear
14
  beta_schedule: linear
15
  epsilon_schedule: linear
 
66
  initialize_from: null
67
  load_model: false
68
  resume: false
69
+ force: true
70
  train_model: false
71
  inference: false
72
  results_dir: results
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:2642:(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 0.081 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: 0.759932 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,22 +166,22 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 41
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
- Peak Allocated memory 17.7 MB
188
  Peak Large allocation bytes 16.0 MB
189
  [ALLOC_TEMP_JOB_1_FRAME]
190
  Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 3616 frames, [64.0 KB-128.0 KB]: 1845 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]: 5461 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 5461 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.082 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: 0.642188 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 44
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.2 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.4 MB
185
  Peak Large allocation bytes 16.0 MB
186
  [ALLOC_TEMP_JOB_1_FRAME]
187
  Initial Block Size 2.0 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 3766 frames, [64.0 KB-128.0 KB]: 1697 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 67.3 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5463 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 5463 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -2,15 +2,15 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.685312271118164,
6
- "min": 1.685312271118164,
7
- "max": 2.8890349864959717,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 16091.361328125,
12
- "min": 16091.361328125,
13
- "max": 29632.33984375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 7.907293319702148,
30
- "min": 0.351300984621048,
31
- "max": 7.907293319702148,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 1541.9222412109375,
36
- "min": 68.15238952636719,
37
- "max": 1584.873046875,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,45 +44,45 @@
44
  "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
- "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
- "value": 0.07125410158957547,
54
- "min": 0.06425344648853164,
55
- "max": 0.0730682620646714,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2850164063583019,
60
- "min": 0.26552707483129134,
61
- "max": 0.35840099343263054,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.2702636673462157,
66
- "min": 0.11407628148456342,
67
- "max": 0.2871631226118873,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 1.0810546693848628,
72
- "min": 0.4563051259382537,
73
- "max": 1.395462342337066,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 2.6940973060000025e-06,
78
- "min": 2.6940973060000025e-06,
79
- "max": 9.729400270599998e-05,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 1.077638922400001e-05,
84
- "min": 1.077638922400001e-05,
85
- "max": 0.0004617200382800001,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
@@ -100,7 +100,7 @@
100
  "SnowballTarget.Policy.Beta.mean": {
101
  "value": 0.0001444306000000001,
102
  "min": 0.0001444306000000001,
103
- "max": 0.0048649706,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
@@ -110,27 +110,27 @@
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 15.727272727272727,
114
- "min": 3.4318181818181817,
115
- "max": 15.727272727272727,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 692.0,
120
- "min": 151.0,
121
- "max": 861.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 15.727272727272727,
126
- "min": 3.4318181818181817,
127
- "max": 15.727272727272727,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 692.0,
132
- "min": 151.0,
133
- "max": 861.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,74 +148,74 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1678034896",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
- "end_time_seconds": "1678035381"
160
  },
161
- "total": 485.3557066640001,
162
  "count": 1,
163
- "self": 0.4400539790001403,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.11385373099994922,
167
  "count": 1,
168
- "self": 0.11385373099994922
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 484.801798954,
172
  "count": 1,
173
- "self": 0.526533777004488,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 8.997876354000027,
177
  "count": 1,
178
- "self": 8.997876354000027
179
  },
180
  "TrainerController.advance": {
181
- "total": 475.1535011999955,
182
- "count": 18202,
183
- "self": 0.2930334490002906,
184
  "children": {
185
  "env_step": {
186
- "total": 474.8604677509952,
187
- "count": 18202,
188
- "self": 329.5822962359972,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 144.98736872400502,
192
- "count": 18202,
193
- "self": 1.5943377219991817,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 143.39303100200584,
197
- "count": 18202,
198
- "self": 30.800351743011106,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
- "total": 112.59267925899474,
202
- "count": 18202,
203
- "self": 112.59267925899474
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
- "total": 0.29080279099298423,
211
- "count": 18202,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
- "total": 483.2114098329995,
216
- "count": 18202,
217
  "is_parallel": true,
218
- "self": 235.90436944599878,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
@@ -224,48 +224,48 @@
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
- "total": 0.004791222000108064,
228
  "count": 1,
229
  "is_parallel": true,
230
- "self": 0.0023365290002175243,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
- "total": 0.00245469299989054,
234
  "count": 10,
235
  "is_parallel": true,
236
- "self": 0.00245469299989054
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
- "total": 0.09479242999998405,
242
  "count": 1,
243
  "is_parallel": true,
244
- "self": 0.0007890579998957037,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
- "total": 0.00041478599996480625,
248
  "count": 1,
249
  "is_parallel": true,
250
- "self": 0.00041478599996480625
251
  },
252
  "communicator.exchange": {
253
- "total": 0.09181369500004166,
254
  "count": 1,
255
  "is_parallel": true,
256
- "self": 0.09181369500004166
257
  },
258
  "steps_from_proto": {
259
- "total": 0.0017748910000818796,
260
  "count": 1,
261
  "is_parallel": true,
262
- "self": 0.0003955619999942428,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
- "total": 0.0013793290000876368,
266
  "count": 10,
267
  "is_parallel": true,
268
- "self": 0.0013793290000876368
269
  }
270
  }
271
  }
@@ -274,34 +274,34 @@
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
- "total": 247.3070403870007,
278
- "count": 18201,
279
  "is_parallel": true,
280
- "self": 10.13541609801348,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
- "total": 5.630104869000434,
284
- "count": 18201,
285
  "is_parallel": true,
286
- "self": 5.630104869000434
287
  },
288
  "communicator.exchange": {
289
- "total": 197.8231598699938,
290
- "count": 18201,
291
  "is_parallel": true,
292
- "self": 197.8231598699938
293
  },
294
  "steps_from_proto": {
295
- "total": 33.71835954999301,
296
- "count": 18201,
297
  "is_parallel": true,
298
- "self": 7.330036332977329,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
- "total": 26.38832321701568,
302
- "count": 182010,
303
  "is_parallel": true,
304
- "self": 26.38832321701568
305
  }
306
  }
307
  }
@@ -316,9 +316,9 @@
316
  }
317
  },
318
  "trainer_threads": {
319
- "total": 0.00011577300006138103,
320
  "count": 1,
321
- "self": 0.00011577300006138103,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
@@ -327,36 +327,36 @@
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
- "total": 471.5583716319643,
331
- "count": 409011,
332
  "is_parallel": true,
333
- "self": 10.690392025921142,
334
  "children": {
335
  "process_trajectory": {
336
- "total": 269.77555193804415,
337
- "count": 409011,
338
  "is_parallel": true,
339
- "self": 268.480037919044,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
- "total": 1.2955140190001657,
343
  "count": 4,
344
  "is_parallel": true,
345
- "self": 1.2955140190001657
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
- "total": 191.092427667999,
351
  "count": 90,
352
  "is_parallel": true,
353
- "self": 66.223011674997,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
- "total": 124.86941599300201,
357
- "count": 4587,
358
  "is_parallel": true,
359
- "self": 124.86941599300201
360
  }
361
  }
362
  }
@@ -367,14 +367,14 @@
367
  }
368
  },
369
  "TrainerController._save_models": {
370
- "total": 0.12377184999991186,
371
  "count": 1,
372
- "self": 0.001011028999755581,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
- "total": 0.12276082100015628,
376
  "count": 1,
377
- "self": 0.12276082100015628
378
  }
379
  }
380
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.4694273471832275,
6
+ "min": 1.4694273471832275,
7
+ "max": 2.877119541168213,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 14110.9111328125,
12
+ "min": 14110.9111328125,
13
+ "max": 29559.52734375,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
 
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 9.996574401855469,
30
+ "min": 0.37617459893226624,
31
+ "max": 9.996574401855469,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 1949.33203125,
36
+ "min": 72.97787475585938,
37
+ "max": 2004.43212890625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
44
  "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
  "count": 20
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06617252733507056,
54
+ "min": 0.06253673741004925,
55
+ "max": 0.07420266700329889,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.26469010934028225,
60
+ "min": 0.250146949640197,
61
+ "max": 0.3511263588024603,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.2408758353222819,
66
+ "min": 0.11121187233982388,
67
+ "max": 0.26978057647452636,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.9635033412891276,
72
+ "min": 0.4448474893592955,
73
+ "max": 1.3489028823726317,
74
  "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 2.6940973060000016e-06,
78
+ "min": 2.6940973060000016e-06,
79
+ "max": 9.729400270600002e-05,
80
  "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.0776389224000007e-05,
84
+ "min": 1.0776389224000007e-05,
85
+ "max": 0.00046172003828000015,
86
  "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
 
100
  "SnowballTarget.Policy.Beta.mean": {
101
  "value": 0.0001444306000000001,
102
  "min": 0.0001444306000000001,
103
+ "max": 0.004864970599999999,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
 
110
  "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 19.886363636363637,
114
+ "min": 2.8636363636363638,
115
+ "max": 19.886363636363637,
116
  "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 875.0,
120
+ "min": 126.0,
121
+ "max": 1091.0,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 19.886363636363637,
126
+ "min": 2.8636363636363638,
127
+ "max": 19.886363636363637,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 875.0,
132
+ "min": 126.0,
133
+ "max": 1091.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1678035791",
152
  "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
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 --force",
154
  "mlagents_version": "0.29.0.dev0",
155
  "mlagents_envs_version": "0.29.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "1.8.1+cu102",
158
  "numpy_version": "1.22.4",
159
+ "end_time_seconds": "1678036335"
160
  },
161
+ "total": 543.5649645139999,
162
  "count": 1,
163
+ "self": 0.785157985000069,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.10759228999995685,
167
  "count": 1,
168
+ "self": 0.10759228999995685
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 542.6722142389999,
172
  "count": 1,
173
+ "self": 0.5381760530101474,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 6.928671871999995,
177
  "count": 1,
178
+ "self": 6.928671871999995
179
  },
180
  "TrainerController.advance": {
181
+ "total": 534.9940004429898,
182
+ "count": 18210,
183
+ "self": 0.27205131597474974,
184
  "children": {
185
  "env_step": {
186
+ "total": 534.721949127015,
187
+ "count": 18210,
188
+ "self": 385.2726056480435,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 149.1597922129954,
192
+ "count": 18210,
193
+ "self": 1.5831741370018335,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 147.57661807599357,
197
+ "count": 18210,
198
+ "self": 32.80984432500395,
199
  "children": {
200
  "TorchPolicy.sample_actions": {
201
+ "total": 114.76677375098961,
202
+ "count": 18210,
203
+ "self": 114.76677375098961
204
  }
205
  }
206
  }
207
  }
208
  },
209
  "workers": {
210
+ "total": 0.28955126597611525,
211
+ "count": 18210,
212
  "self": 0.0,
213
  "children": {
214
  "worker_root": {
215
+ "total": 541.0359419470033,
216
+ "count": 18210,
217
  "is_parallel": true,
218
+ "self": 291.9733024630241,
219
  "children": {
220
  "run_training.setup": {
221
  "total": 0.0,
 
224
  "self": 0.0,
225
  "children": {
226
  "steps_from_proto": {
227
+ "total": 0.0022754120000172406,
228
  "count": 1,
229
  "is_parallel": true,
230
+ "self": 0.0007699310003772553,
231
  "children": {
232
  "_process_rank_one_or_two_observation": {
233
+ "total": 0.0015054809996399854,
234
  "count": 10,
235
  "is_parallel": true,
236
+ "self": 0.0015054809996399854
237
  }
238
  }
239
  },
240
  "UnityEnvironment.step": {
241
+ "total": 0.05132571000012831,
242
  "count": 1,
243
  "is_parallel": true,
244
+ "self": 0.0006334280001283332,
245
  "children": {
246
  "UnityEnvironment._generate_step_input": {
247
+ "total": 0.0004171319999386469,
248
  "count": 1,
249
  "is_parallel": true,
250
+ "self": 0.0004171319999386469
251
  },
252
  "communicator.exchange": {
253
+ "total": 0.04818544599993402,
254
  "count": 1,
255
  "is_parallel": true,
256
+ "self": 0.04818544599993402
257
  },
258
  "steps_from_proto": {
259
+ "total": 0.0020897040001273126,
260
  "count": 1,
261
  "is_parallel": true,
262
+ "self": 0.0005734110000048531,
263
  "children": {
264
  "_process_rank_one_or_two_observation": {
265
+ "total": 0.0015162930001224595,
266
  "count": 10,
267
  "is_parallel": true,
268
+ "self": 0.0015162930001224595
269
  }
270
  }
271
  }
 
274
  }
275
  },
276
  "UnityEnvironment.step": {
277
+ "total": 249.06263948397918,
278
+ "count": 18209,
279
  "is_parallel": true,
280
+ "self": 9.97293427995669,
281
  "children": {
282
  "UnityEnvironment._generate_step_input": {
283
+ "total": 5.687937014006593,
284
+ "count": 18209,
285
  "is_parallel": true,
286
+ "self": 5.687937014006593
287
  },
288
  "communicator.exchange": {
289
+ "total": 199.5349575030209,
290
+ "count": 18209,
291
  "is_parallel": true,
292
+ "self": 199.5349575030209
293
  },
294
  "steps_from_proto": {
295
+ "total": 33.866810686994995,
296
+ "count": 18209,
297
  "is_parallel": true,
298
+ "self": 7.550632629977827,
299
  "children": {
300
  "_process_rank_one_or_two_observation": {
301
+ "total": 26.31617805701717,
302
+ "count": 182090,
303
  "is_parallel": true,
304
+ "self": 26.31617805701717
305
  }
306
  }
307
  }
 
316
  }
317
  },
318
  "trainer_threads": {
319
+ "total": 0.00013248899995232932,
320
  "count": 1,
321
+ "self": 0.00013248899995232932,
322
  "children": {
323
  "thread_root": {
324
  "total": 0.0,
 
327
  "self": 0.0,
328
  "children": {
329
  "trainer_advance": {
330
+ "total": 531.2292537309627,
331
+ "count": 410466,
332
  "is_parallel": true,
333
+ "self": 11.0115854399196,
334
  "children": {
335
  "process_trajectory": {
336
+ "total": 271.62298273604074,
337
+ "count": 410466,
338
  "is_parallel": true,
339
+ "self": 270.561674838041,
340
  "children": {
341
  "RLTrainer._checkpoint": {
342
+ "total": 1.061307897999768,
343
  "count": 4,
344
  "is_parallel": true,
345
+ "self": 1.061307897999768
346
  }
347
  }
348
  },
349
  "_update_policy": {
350
+ "total": 248.59468555500234,
351
  "count": 90,
352
  "is_parallel": true,
353
+ "self": 97.310092754994,
354
  "children": {
355
  "TorchPPOOptimizer.update": {
356
+ "total": 151.28459280000834,
357
+ "count": 7645,
358
  "is_parallel": true,
359
+ "self": 151.28459280000834
360
  }
361
  }
362
  }
 
367
  }
368
  },
369
  "TrainerController._save_models": {
370
+ "total": 0.21123338200004582,
371
  "count": 1,
372
+ "self": 0.002096945999937816,
373
  "children": {
374
  "RLTrainer._checkpoint": {
375
+ "total": 0.209136436000108,
376
  "count": 1,
377
+ "self": 0.209136436000108
378
  }
379
  }
380
  }
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": 9.090909090909092,
8
- "creation_time": 1678035026.4217668,
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": 12.636363636363637,
17
- "creation_time": 1678035146.9150894,
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": 15.909090909090908,
26
- "creation_time": 1678035265.6009245,
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": 15.636363636363637,
35
- "creation_time": 1678035381.3155072,
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": 15.636363636363637,
44
- "creation_time": 1678035381.4671304,
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": 15.636363636363637,
54
- "creation_time": 1678035381.4671304,
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": 9.0,
8
+ "creation_time": 1678035931.8002622,
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": 16.09090909090909,
17
+ "creation_time": 1678036066.813796,
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": 16.181818181818183,
26
+ "creation_time": 1678036201.2113643,
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": 19.636363636363637,
35
+ "creation_time": 1678036334.4560852,
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": 19.636363636363637,
44
+ "creation_time": 1678036334.7086399,
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": 19.636363636363637,
54
+ "creation_time": 1678036334.7086399,
55
  "auxillary_file_paths": [
56
  "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]