Hugging Face's logo

FredericProtat
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files
xet
Metrics Community
FredericProtat commited on
Commit
53d5cb0
·
1 Parent(s): dd0633b

First Push

Browse files
Files changed (16) hide show
  1. SnowballTarget.onnx +1 -1
  2. SnowballTarget/SnowballTarget-1000208.onnx +3 -0
  3. SnowballTarget/SnowballTarget-1000208.pt +3 -0
  4. SnowballTarget/SnowballTarget-899992.onnx +3 -0
  5. SnowballTarget/SnowballTarget-899992.pt +3 -0
  6. SnowballTarget/SnowballTarget-949992.onnx +3 -0
  7. SnowballTarget/SnowballTarget-949992.pt +3 -0
  8. SnowballTarget/SnowballTarget-999952.onnx +3 -0
  9. SnowballTarget/SnowballTarget-999952.pt +3 -0
  10. SnowballTarget/checkpoint.pt +1 -1
  11. SnowballTarget/events.out.tfevents.1692789586.4bcb54d8d662.10981.0 +3 -0
  12. config.json +1 -1
  13. configuration.yaml +3 -3
  14. run_logs/Player-0.log +15 -18
  15. run_logs/timers.json +160 -160
  16. run_logs/training_status.json +25 -34
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9498d0dc5253c1fcf8d470ffe84d7652e51dc530864256840c3c556c15fd4c80
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a8bda6bbed144b3b8b0acbb3b21dd6f6ff56cca0fe24801e2b1afe4302c5a9
3
  size 646532
SnowballTarget/SnowballTarget-1000208.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a8bda6bbed144b3b8b0acbb3b21dd6f6ff56cca0fe24801e2b1afe4302c5a9
3
+ size 646532
SnowballTarget/SnowballTarget-1000208.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113f51a52188a8b3b494606ec029a9b129dbaeffb1915c921fae5e2493340ce0
3
+ size 3843968
SnowballTarget/SnowballTarget-899992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0f256b08a61a7e1532518b25f408dbbc241f87ae7f7da9cbfda5930f97c787
3
+ size 646532
SnowballTarget/SnowballTarget-899992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a277234039cc39fad0f6cb02c8df204e9d8013f4d753655f64ed738b2efe45
3
+ size 3843968
SnowballTarget/SnowballTarget-949992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21023e94f103453bf7cebda4227ebcfff70282138f851237f029bb7ba03d7152
3
+ size 646532
SnowballTarget/SnowballTarget-949992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bab41accc610cb4296192a0a22987fa084707f6e6f689a8d08d421127de766
3
+ size 3843968
SnowballTarget/SnowballTarget-999952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a8bda6bbed144b3b8b0acbb3b21dd6f6ff56cca0fe24801e2b1afe4302c5a9
3
+ size 646532
SnowballTarget/SnowballTarget-999952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22a0494d4d28963b4993b01f455bf11870cf2225ef091949c2ad10ced9fca09
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c6a9063de89b54ee993b2cf3b2b567597b277e6371c3b0dea46f42fbe004a43
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113f51a52188a8b3b494606ec029a9b129dbaeffb1915c921fae5e2493340ce0
3
  size 3843968
SnowballTarget/events.out.tfevents.1692789586.4bcb54d8d662.10981.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1265284d7bcac7996f85e6c7c9eb3aaa732ced162823806f01b8e7f843d01f8f
3
+ size 93801
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": 4, "even_checkpoints": false, "max_steps": 1000000, "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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -36,9 +36,9 @@ behaviors:
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
- keep_checkpoints: 10
40
  even_checkpoints: false
41
- max_steps: 200000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
@@ -64,7 +64,7 @@ engine_settings:
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
- run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
  resume: false
 
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
+ keep_checkpoints: 4
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
64
  no_graphics: true
65
  environment_parameters: null
66
  checkpoint_settings:
67
+ run_id: SnowballTarget2
68
  initialize_from: null
69
  load_model: false
70
  resume: false
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.085 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: 0.697151 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 40
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 6.9 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 17.6 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]: 4278 frames, [64.0 KB-128.0 KB]: 1183 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]: 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 0.132 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: 0.864386 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]: 26826 frames, [16.0 KB-32.0 KB]: 454 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]: 11368 frames, [8.0 MB-16.0 MB]: 15913 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 14.5 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 27281 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
+ Peak Allocated memory 17.7 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]: 25920 frames, [64.0 KB-128.0 KB]: 1361 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
  Peak Allocated memory 66.8 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 27281 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]: 27281 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]: 27280 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]: 27281 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]: 27281 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
@@ -2,213 +2,213 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 1.0579354763031006,
6
- "min": 1.0579354763031006,
7
- "max": 2.8633360862731934,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10112.8056640625,
12
- "min": 10112.8056640625,
13
- "max": 29323.42578125,
14
- "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
- "value": 199984.0,
18
  "min": 9952.0,
19
- "max": 199984.0,
20
- "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
- "value": 199984.0,
24
  "min": 9952.0,
25
- "max": 199984.0,
26
- "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
- "value": 12.487752914428711,
30
- "min": 0.4639379680156708,
31
- "max": 12.487752914428711,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2435.11181640625,
36
- "min": 90.00396728515625,
37
- "max": 2508.46142578125,
38
- "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
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": 0.07102292626672459,
54
- "min": 0.06343388449999575,
55
- "max": 0.07197926300212595,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.28409170506689835,
60
- "min": 0.253735537999983,
61
- "max": 0.35989631501062974,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.20272402998571304,
66
- "min": 0.11520260382859109,
67
- "max": 0.29187969702715966,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8108961199428522,
72
- "min": 0.46081041531436434,
73
- "max": 1.3355596275890576,
74
- "count": 20
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
- "value": 8.082097306000005e-06,
78
- "min": 8.082097306000005e-06,
79
- "max": 0.000291882002706,
80
- "count": 20
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
- "value": 3.232838922400002e-05,
84
- "min": 3.232838922400002e-05,
85
- "max": 0.00138516003828,
86
- "count": 20
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
- "value": 0.10269400000000001,
90
- "min": 0.10269400000000001,
91
- "max": 0.19729400000000002,
92
- "count": 20
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
- "value": 0.41077600000000003,
96
- "min": 0.41077600000000003,
97
- "max": 0.96172,
98
- "count": 20
99
  },
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": {
107
- "value": 0.0005777224000000004,
108
- "min": 0.0005777224000000004,
109
- "max": 0.023089828,
110
- "count": 20
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
- "value": 24.272727272727273,
114
- "min": 3.3636363636363638,
115
- "max": 24.927272727272726,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1068.0,
120
- "min": 148.0,
121
- "max": 1371.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 24.272727272727273,
126
- "min": 3.3636363636363638,
127
- "max": 24.927272727272726,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1068.0,
132
- "min": 148.0,
133
- "max": 1371.0,
134
- "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
- "count": 20
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
- "count": 20
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1692787520",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
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": "0.31.0.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": "1692788053"
160
  },
161
- "total": 533.3497881160001,
162
  "count": 1,
163
- "self": 0.843377463000138,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.044987374000015734,
167
  "count": 1,
168
- "self": 0.044987374000015734
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 532.461423279,
172
  "count": 1,
173
- "self": 0.6943053169962923,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 4.251182921000009,
177
  "count": 1,
178
- "self": 4.251182921000009
179
  },
180
  "TrainerController.advance": {
181
- "total": 527.2508416390036,
182
- "count": 18203,
183
- "self": 0.3213442830065105,
184
  "children": {
185
  "env_step": {
186
- "total": 526.9294973559971,
187
- "count": 18203,
188
- "self": 384.4014601269955,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 142.19240750699976,
192
- "count": 18203,
193
- "self": 1.9161274759908906,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 140.27628003100887,
197
- "count": 18203,
198
- "self": 140.27628003100887
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.3356297220018405,
204
- "count": 18203,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 530.3815450409995,
209
- "count": 18203,
210
  "is_parallel": true,
211
- "self": 247.07870601000252,
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": 0.00605969000002915,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004331141000022853,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0017285490000062964,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0017285490000062964
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.11363429800002223,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006955780000339473,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00041432099999383354,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00041432099999383354
244
  },
245
  "communicator.exchange": {
246
- "total": 0.10702405400002135,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.10702405400002135
250
  },
251
  "steps_from_proto": {
252
- "total": 0.005500344999973095,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00047370099991894676,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.005026644000054148,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.005026644000054148
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 283.302839030997,
271
- "count": 18202,
272
  "is_parallel": true,
273
- "self": 11.741127726004095,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 6.114336217984373,
277
- "count": 18202,
278
  "is_parallel": true,
279
- "self": 6.114336217984373
280
  },
281
  "communicator.exchange": {
282
- "total": 222.89538783600335,
283
- "count": 18202,
284
  "is_parallel": true,
285
- "self": 222.89538783600335
286
  },
287
  "steps_from_proto": {
288
- "total": 42.55198725100519,
289
- "count": 18202,
290
  "is_parallel": true,
291
- "self": 7.934983261018317,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 34.61700398998687,
295
- "count": 182020,
296
  "is_parallel": true,
297
- "self": 34.61700398998687
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.0002595210000890802,
313
  "count": 1,
314
- "self": 0.0002595210000890802,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 522.8277953369843,
324
- "count": 498300,
325
  "is_parallel": true,
326
- "self": 12.491036175976433,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 287.07902266900805,
330
- "count": 498300,
331
  "is_parallel": true,
332
- "self": 285.6179228650079,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.4610998040001277,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 1.4610998040001277
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 223.25773649199982,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 86.58435530100417,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 136.67338119099566,
350
- "count": 4584,
351
  "is_parallel": true,
352
- "self": 136.67338119099566
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.26483388099995864,
364
  "count": 1,
365
- "self": 0.001244551999889154,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.2635893290000695,
369
  "count": 1,
370
- "self": 0.2635893290000695
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6263381242752075,
6
+ "min": 0.6099420189857483,
7
+ "max": 2.8710243701934814,
8
+ "count": 100
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 5959.607421875,
12
+ "min": 5878.59814453125,
13
+ "max": 29433.7421875,
14
+ "count": 100
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999952.0,
18
  "min": 9952.0,
19
+ "max": 999952.0,
20
+ "count": 100
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999952.0,
24
  "min": 9952.0,
25
+ "max": 999952.0,
26
+ "count": 100
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.241153717041016,
30
+ "min": 0.2647833526134491,
31
+ "max": 14.308838844299316,
32
+ "count": 100
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2777.02490234375,
36
+ "min": 51.36796951293945,
37
+ "max": 2933.31201171875,
38
+ "count": 100
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 100
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
  "value": 8756.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 100
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07168237034085334,
54
+ "min": 0.059774956651666544,
55
+ "max": 0.07474352938394684,
56
+ "count": 100
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.28672948136341336,
60
+ "min": 0.23909982660666618,
61
+ "max": 0.3718264155887643,
62
+ "count": 100
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.1699091669756408,
66
+ "min": 0.10359750530344672,
67
+ "max": 0.29772844216695016,
68
+ "count": 100
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.6796366679025632,
72
+ "min": 0.4143900212137869,
73
+ "max": 1.3277685618868063,
74
+ "count": 100
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 1.3764995412000027e-06,
78
+ "min": 1.3764995412000027e-06,
79
+ "max": 0.0002983764005411999,
80
+ "count": 100
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 5.505998164800011e-06,
84
+ "min": 5.505998164800011e-06,
85
+ "max": 0.001477032007656,
86
+ "count": 100
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10045880000000001,
90
+ "min": 0.10045880000000001,
91
+ "max": 0.1994588,
92
+ "count": 100
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.40183520000000006,
96
+ "min": 0.40183520000000006,
97
+ "max": 0.992344,
98
+ "count": 100
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 3.289412000000004e-05,
102
+ "min": 3.289412000000004e-05,
103
+ "max": 0.00497299412,
104
+ "count": 100
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.00013157648000000017,
108
+ "min": 0.00013157648000000017,
109
+ "max": 0.0246179656,
110
+ "count": 100
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 27.755555555555556,
114
+ "min": 2.977272727272727,
115
+ "max": 28.204545454545453,
116
+ "count": 100
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1249.0,
120
+ "min": 131.0,
121
+ "max": 1535.0,
122
+ "count": 100
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 27.755555555555556,
126
+ "min": 2.977272727272727,
127
+ "max": 28.204545454545453,
128
+ "count": 100
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1249.0,
132
+ "min": 131.0,
133
+ "max": 1535.0,
134
+ "count": 100
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 100
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 100
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1692789584",
152
  "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
154
  "mlagents_version": "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": "1692792202"
160
  },
161
+ "total": 2617.866121536,
162
  "count": 1,
163
+ "self": 0.4756141009993371,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.041511875000196596,
167
  "count": 1,
168
+ "self": 0.041511875000196596
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2617.3489955600003,
172
  "count": 1,
173
+ "self": 3.2549041718830267,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 5.402893438999854,
177
  "count": 1,
178
+ "self": 5.402893438999854
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2608.541486187118,
182
+ "count": 90936,
183
+ "self": 1.6858274100941344,
184
  "children": {
185
  "env_step": {
186
+ "total": 2606.855658777024,
187
+ "count": 90936,
188
+ "self": 1904.5304624860273,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 700.650388346,
192
+ "count": 90936,
193
+ "self": 10.031359933954718,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 690.6190284120453,
197
+ "count": 90936,
198
+ "self": 690.6190284120453
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.6748079449967008,
204
+ "count": 90936,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2608.446949953981,
209
+ "count": 90936,
210
  "is_parallel": true,
211
+ "self": 1203.8605284880277,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.004731805000119493,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0008445630005553539,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0038872419995641394,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0038872419995641394
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0405589670003792,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000767445000292355,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000366217000191682,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000366217000191682
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03615702799970677,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03615702799970677
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.003268277000188391,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.0007957499997246487,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0024725270004637423,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0024725270004637423
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1404.5864214659532,
271
+ "count": 90935,
272
  "is_parallel": true,
273
+ "self": 57.51829756198731,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 30.290380998103956,
277
+ "count": 90935,
278
  "is_parallel": true,
279
+ "self": 30.290380998103956
280
  },
281
  "communicator.exchange": {
282
+ "total": 1107.2918465998964,
283
+ "count": 90935,
284
  "is_parallel": true,
285
+ "self": 1107.2918465998964
286
  },
287
  "steps_from_proto": {
288
+ "total": 209.48589630596553,
289
+ "count": 90935,
290
  "is_parallel": true,
291
+ "self": 39.24883937802588,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 170.23705692793965,
295
+ "count": 909350,
296
  "is_parallel": true,
297
+ "self": 170.23705692793965
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00020981899979233276,
313
  "count": 1,
314
+ "self": 0.00020981899979233276,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 2587.560842958052,
324
+ "count": 2419961,
325
  "is_parallel": true,
326
+ "self": 56.73670174613926,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 1423.1495705799089,
330
+ "count": 2419961,
331
  "is_parallel": true,
332
+ "self": 1417.1538558439106,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 5.995714735998263,
336
+ "count": 20,
337
  "is_parallel": true,
338
+ "self": 5.995714735998263
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 1107.674570632004,
344
+ "count": 454,
345
  "is_parallel": true,
346
+ "self": 438.3198206990437,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 669.3547499329602,
350
+ "count": 23151,
351
  "is_parallel": true,
352
+ "self": 669.3547499329602
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.14950194299944997,
364
  "count": 1,
365
+ "self": 0.0009423860001334106,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.14855955699931656,
369
  "count": 1,
370
+ "self": 0.14855955699931656
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,49 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.181818181818182,
8
- "creation_time": 1692787656.9875243,
9
  "auxillary_file_paths": [
10
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
  ]
12
  },
13
  {
14
- "steps": 99960,
15
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
- "reward": 19.818181818181817,
17
- "creation_time": 1692787788.7703097,
18
  "auxillary_file_paths": [
19
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
  ]
21
  },
22
  {
23
- "steps": 149984,
24
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
- "reward": 23.727272727272727,
26
- "creation_time": 1692787919.9585946,
27
  "auxillary_file_paths": [
28
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
  ]
30
  },
31
  {
32
- "steps": 199984,
33
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
- "reward": 25.272727272727273,
35
- "creation_time": 1692788052.227202,
36
  "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200200,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.onnx",
43
- "reward": 25.363636363636363,
44
- "creation_time": 1692788052.5668948,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200200,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 25.363636363636363,
54
- "creation_time": 1692788052.5668948,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200200.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 899992,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-899992.onnx",
7
+ "reward": 26.636363636363637,
8
+ "creation_time": 1692791946.1620522,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-899992.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 949992,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-949992.onnx",
16
+ "reward": 28.545454545454547,
17
+ "creation_time": 1692792072.9445312,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-949992.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 999952,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.onnx",
25
+ "reward": 27.363636363636363,
26
+ "creation_time": 1692792202.0374892,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 1000208,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.onnx",
34
+ "reward": 27.363636363636363,
35
+ "creation_time": 1692792202.222817,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.pt"
 
 
 
 
 
 
 
 
 
38
  ]
39
  }
40
  ],
41
  "final_checkpoint": {
42
+ "steps": 1000208,
43
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
44
+ "reward": 27.363636363636363,
45
+ "creation_time": 1692792202.222817,
46
  "auxillary_file_paths": [
47
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.pt"
48
  ]
49
  }
50
  },