Hugging Face's logo

chradden
/
ppo-SnowballTarget

Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Model card Files Metrics Community
chradden commited on
Commit
29d4e09
•
1 Parent(s): cd799d7

First Push

Browse files
Files changed (18) hide show
  1. SnowballTarget.onnx +2 -2
  2. SnowballTarget/SnowballTarget-199984.pt +0 -3
  3. SnowballTarget/SnowballTarget-200112.pt +0 -3
  4. SnowballTarget/SnowballTarget-49936.onnx +0 -3
  5. SnowballTarget/SnowballTarget-49936.pt +0 -3
  6. SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-499976.onnx} +2 -2
  7. SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-499976.pt} +2 -2
  8. SnowballTarget/{SnowballTarget-200112.onnx → SnowballTarget-500104.onnx} +2 -2
  9. SnowballTarget/{SnowballTarget-199984.onnx → SnowballTarget-500104.pt} +2 -2
  10. SnowballTarget/SnowballTarget-99960.onnx +0 -3
  11. SnowballTarget/SnowballTarget-99960.pt +0 -3
  12. SnowballTarget/checkpoint.pt +2 -2
  13. SnowballTarget/{events.out.tfevents.1679674832.1e68e03a1426.3511.0 → events.out.tfevents.1679676297.1e68e03a1426.10013.0} +2 -2
  14. config.json +1 -1
  15. configuration.yaml +9 -9
  16. run_logs/Player-0.log +14 -17
  17. run_logs/timers.json +186 -201
  18. run_logs/training_status.json +15 -42
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6953aec98896532e13b16df8475ad346d4f0e743d46dc77f7997328c46942d6
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e5994f9c491e44933f9ddf1ab2538ef6c80a21570b442a68a8df17c9b632ec
3
+ size 260484
SnowballTarget/SnowballTarget-199984.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23f581165b210ed903d86995dd6b9daa1caab48863f2bef7ce1274af6d23ce6d
3
- size 3843968
 
 
 
 
SnowballTarget/SnowballTarget-200112.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e0a8c3d73c4d2afa3c11ab7821f95a0eb974169ac7ee1c5f21e3541641feaa
3
- size 3843968
 
 
 
 
SnowballTarget/SnowballTarget-49936.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:94e965b1a9d7cda0a9250c3bd08f2df13751fd8b4d89a0213f7747a3177bf6d5
3
- size 646532
 
 
 
 
SnowballTarget/SnowballTarget-49936.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d17c1e40385e91228c5c21b0d8948912ba809de5fbbf3992abb956617f10683
3
- size 3843968
 
 
 
 
SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-499976.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bcc17932370e3a4bf239bc0bf242b3821e75187e61c32329b5fa661ca408dd3
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e5994f9c491e44933f9ddf1ab2538ef6c80a21570b442a68a8df17c9b632ec
3
+ size 260484
SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-499976.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c59f8e4a5b555d688eb45898fac436a2a1362f6ecc5b1c69db7f0b3e4be6df9a
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d159df3ea8d0fd9f5f321aca9b686e774a7645d79370373f89d193efcc82c84
3
+ size 1538304
SnowballTarget/{SnowballTarget-200112.onnx → SnowballTarget-500104.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6953aec98896532e13b16df8475ad346d4f0e743d46dc77f7997328c46942d6
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e5994f9c491e44933f9ddf1ab2538ef6c80a21570b442a68a8df17c9b632ec
3
+ size 260484
SnowballTarget/{SnowballTarget-199984.onnx → SnowballTarget-500104.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6953aec98896532e13b16df8475ad346d4f0e743d46dc77f7997328c46942d6
3
- size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c5be8a9cd8f9daeda78bc74b975a25bcec037ffadb261a0f120e4b5b125e47
3
+ size 1538304
SnowballTarget/SnowballTarget-99960.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ab493ebb46f7ab319a29a997c46d0aec46faa56d31a5cc923547e600b7fd1dc
3
- size 646532
 
 
 
 
SnowballTarget/SnowballTarget-99960.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6e1019793e66b9249840e9d86ebf8befa6ba7eccf005355ee1bc381e6cc3070
3
- size 3843968
 
 
 
 
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e0a8c3d73c4d2afa3c11ab7821f95a0eb974169ac7ee1c5f21e3541641feaa
3
- size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c5be8a9cd8f9daeda78bc74b975a25bcec037ffadb261a0f120e4b5b125e47
3
+ size 1538304
SnowballTarget/{events.out.tfevents.1679674832.1e68e03a1426.3511.0 → events.out.tfevents.1679676297.1e68e03a1426.10013.0} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1142373d688a004033fbe27858491ed6b72a77366ce19dd9e23337e5b85998b9
3
- size 23750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44a53aa8c52c7309a30bb61c76af27df40e6c9d17102bf877efaeafcfd17b0a
3
+ size 15237
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": 512, "buffer_size": 10240, "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": 500000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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
@@ -3,8 +3,8 @@ behaviors:
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
- batch_size: 128
7
- buffer_size: 2048
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
@@ -14,10 +14,10 @@ behaviors:
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
- checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
- hidden_units: 256
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
@@ -36,12 +36,12 @@ 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
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
@@ -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
 
3
  SnowballTarget:
4
  trainer_type: ppo
5
  hyperparameters:
6
+ batch_size: 512
7
+ buffer_size: 10240
8
  learning_rate: 0.0003
9
  beta: 0.005
10
  epsilon: 0.2
 
14
  learning_rate_schedule: linear
15
  beta_schedule: linear
16
  epsilon_schedule: linear
17
+ checkpoint_interval: 500000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 128
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
36
  goal_conditioning_type: hyper
37
  deterministic: false
38
  init_path: null
39
+ keep_checkpoints: 5
40
  even_checkpoints: false
41
+ max_steps: 500000
42
  time_horizon: 64
43
+ summary_freq: 50000
44
+ threaded: false
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
 
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: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 0.085 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: 0.665836 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]: 5370 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
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 37
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]: 5462 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 6.6 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 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]: 4269 frames, [64.0 KB-128.0 KB]: 1193 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]: 5462 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]: 5462 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]: 5461 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]: 5462 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]: 5462 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 0.076 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: 0.713996 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]: 13412 frames, [16.0 KB-32.0 KB]: 227 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 39
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]: 13313 frames, [8.0 MB-16.0 MB]: 327 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 9.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 13640 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 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]: 12246 frames, [64.0 KB-128.0 KB]: 1394 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.4 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 13640 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]: 13640 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]: 13639 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]: 13640 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]: 13640 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": 1.1322945356369019,
6
- "min": 1.1322945356369019,
7
- "max": 2.8558342456817627,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 10848.513671875,
12
- "min": 10848.513671875,
13
- "max": 29278.01171875,
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": 11.974501609802246,
30
- "min": 0.4376535713672638,
31
- "max": 11.974501609802246,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2335.02783203125,
36
- "min": 84.90479278564453,
37
- "max": 2398.787841796875,
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": 0.06677463126800598,
54
- "min": 0.060284501939100205,
55
- "max": 0.07628564718784307,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2670985250720239,
60
- "min": 0.24113800775640082,
61
- "max": 0.3767743916724416,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.211860485009703,
66
- "min": 0.10933664314535575,
67
- "max": 0.2908311834522322,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.847441940038812,
72
- "min": 0.437346572581423,
73
- "max": 1.454155917261161,
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": 23.954545454545453,
114
- "min": 3.272727272727273,
115
- "max": 23.954545454545453,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1054.0,
120
- "min": 144.0,
121
- "max": 1291.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.954545454545453,
126
- "min": 3.272727272727273,
127
- "max": 23.954545454545453,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1054.0,
132
- "min": 144.0,
133
- "max": 1291.0,
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": "1679674826",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679675284"
160
  },
161
- "total": 458.05725936299996,
162
  "count": 1,
163
- "self": 0.38120635099983247,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.10415301900002305,
167
  "count": 1,
168
- "self": 0.10415301900002305
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 457.5718999930001,
172
  "count": 1,
173
- "self": 0.531236218999652,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.789148635999936,
177
  "count": 1,
178
- "self": 9.789148635999936
179
  },
180
  "TrainerController.advance": {
181
- "total": 447.1038243300004,
182
- "count": 18205,
183
- "self": 0.27114537599527466,
184
  "children": {
185
  "env_step": {
186
- "total": 446.83267895400513,
187
- "count": 18205,
188
- "self": 323.02302907798696,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 123.54844523900294,
192
- "count": 18205,
193
- "self": 2.042846366021763,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 121.50559887298118,
197
- "count": 18205,
198
- "self": 121.50559887298118
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.26120463701522567,
204
- "count": 18205,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 456.05685000499545,
209
- "count": 18205,
210
  "is_parallel": true,
211
- "self": 216.83978242399007,
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": 0.004980694999972002,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.003484442000285526,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.001496252999686476,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.001496252999686476
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.043805836999922576,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.000545662000035918,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0002816219999886016,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0002816219999886016
244
  },
245
  "communicator.exchange": {
246
- "total": 0.04110232799996538,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.04110232799996538
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0018762249999326741,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00038694599959399056,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0014892790003386835,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0014892790003386835
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 239.21706758100538,
271
- "count": 18204,
272
  "is_parallel": true,
273
- "self": 9.495424125030581,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.198842343005708,
277
- "count": 18204,
278
  "is_parallel": true,
279
- "self": 5.198842343005708
280
  },
281
  "communicator.exchange": {
282
- "total": 193.7265980409777,
283
- "count": 18204,
284
  "is_parallel": true,
285
- "self": 193.7265980409777
286
  },
287
  "steps_from_proto": {
288
- "total": 30.796203071991386,
289
- "count": 18204,
290
  "is_parallel": true,
291
- "self": 6.041371538006274,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 24.75483153398511,
295
- "count": 182040,
296
  "is_parallel": true,
297
- "self": 24.75483153398511
298
  }
299
  }
300
  }
@@ -305,53 +305,33 @@
305
  }
306
  }
307
  }
308
- }
309
- }
310
- },
311
- "trainer_threads": {
312
- "total": 0.0001591729999290692,
313
- "count": 1,
314
- "self": 0.0001591729999290692,
315
- "children": {
316
- "thread_root": {
317
- "total": 0.0,
318
- "count": 0,
319
- "is_parallel": true,
320
- "self": 0.0,
321
  "children": {
322
- "trainer_advance": {
323
- "total": 443.8729001199465,
324
- "count": 407662,
325
- "is_parallel": true,
326
- "self": 9.504065423941142,
327
  "children": {
328
- "process_trajectory": {
329
- "total": 246.4948647380046,
330
- "count": 407662,
331
- "is_parallel": true,
332
- "self": 245.60826828500456,
333
- "children": {
334
- "RLTrainer._checkpoint": {
335
- "total": 0.8865964530000383,
336
- "count": 4,
337
- "is_parallel": true,
338
- "self": 0.8865964530000383
339
- }
340
- }
341
- },
342
- "_update_policy": {
343
- "total": 187.87396995800077,
344
- "count": 90,
345
- "is_parallel": true,
346
- "self": 70.26837018799858,
347
- "children": {
348
- "TorchPPOOptimizer.update": {
349
- "total": 117.60559977000219,
350
- "count": 4587,
351
- "is_parallel": true,
352
- "self": 117.60559977000219
353
- }
354
- }
355
  }
356
  }
357
  }
@@ -359,15 +339,20 @@
359
  }
360
  }
361
  },
 
 
 
 
 
362
  "TrainerController._save_models": {
363
- "total": 0.14753163500017763,
364
  "count": 1,
365
- "self": 0.0009338040001694026,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.14659783100000823,
369
  "count": 1,
370
- "self": 0.14659783100000823
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 1.0808089971542358,
6
+ "min": 1.0808089971542358,
7
+ "max": 2.8161678314208984,
8
+ "count": 10
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 53928.04296875,
12
+ "min": 53928.04296875,
13
+ "max": 142250.265625,
14
+ "count": 10
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499976.0,
18
+ "min": 49936.0,
19
+ "max": 499976.0,
20
+ "count": 10
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499976.0,
24
+ "min": 49936.0,
25
+ "max": 499976.0,
26
+ "count": 10
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 12.410496711730957,
30
+ "min": 0.4977417588233948,
31
+ "max": 12.410496711730957,
32
+ "count": 10
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 12447.728515625,
36
+ "min": 493.75982666015625,
37
+ "max": 12447.728515625,
38
+ "count": 10
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 10
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 50347.0,
48
+ "min": 48158.0,
49
+ "max": 50347.0,
50
+ "count": 10
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 25.450592885375492,
54
+ "min": 4.421487603305785,
55
+ "max": 25.450592885375492,
56
+ "count": 10
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 6439.0,
60
+ "min": 1070.0,
61
+ "max": 6439.0,
62
+ "count": 10
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 25.450592885375492,
66
+ "min": 4.421487603305785,
67
+ "max": 25.450592885375492,
68
+ "count": 10
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 6439.0,
72
+ "min": 1070.0,
73
+ "max": 6439.0,
74
+ "count": 10
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.034703764460784214,
78
+ "min": 0.03092670888682545,
79
+ "max": 0.03544381486771026,
80
+ "count": 10
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 0.13881505784313686,
84
+ "min": 0.1237068355473018,
85
+ "max": 0.17675379196891933,
86
+ "count": 10
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.2332314179441522,
90
+ "min": 0.14866675968681062,
91
+ "max": 0.29265326806713665,
92
+ "count": 10
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 0.9329256717766088,
96
+ "min": 0.5946670387472425,
97
+ "max": 1.4632663403356831,
98
+ "count": 10
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 1.4576495141200002e-05,
102
+ "min": 1.4576495141200002e-05,
103
+ "max": 0.0002841864052712,
104
+ "count": 10
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 5.830598056480001e-05,
108
+ "min": 5.830598056480001e-05,
109
+ "max": 0.0012797184734272,
110
+ "count": 10
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.1048588,
114
+ "min": 0.1048588,
115
+ "max": 0.19472880000000004,
116
+ "count": 10
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 0.4194352,
120
+ "min": 0.4194352,
121
+ "max": 0.9265728,
122
+ "count": 10
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.00025245412,
126
+ "min": 0.00025245412,
127
+ "max": 0.00473696712,
128
+ "count": 10
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.00100981648,
132
+ "min": 0.00100981648,
133
+ "max": 0.021335982719999997,
134
+ "count": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 10
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 10
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1679676294",
152
  "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=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": "1679677205"
160
  },
161
+ "total": 911.534228516,
162
  "count": 1,
163
+ "self": 0.43875345300057234,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.11191284099959375,
167
  "count": 1,
168
+ "self": 0.11191284099959375
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 910.9835622219998,
172
  "count": 1,
173
+ "self": 0.8819165700397207,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 6.801290793999669,
177
  "count": 1,
178
+ "self": 6.801290793999669
179
  },
180
  "TrainerController.advance": {
181
+ "total": 903.1545492259606,
182
+ "count": 45464,
183
+ "self": 0.9160812480081404,
184
  "children": {
185
  "env_step": {
186
+ "total": 693.2853571709693,
187
+ "count": 45464,
188
+ "self": 565.7987313059598,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 126.94533476202605,
192
+ "count": 45464,
193
+ "self": 6.381621722028285,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 120.56371303999777,
197
+ "count": 45464,
198
+ "self": 120.56371303999777
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.5412911029834504,
204
+ "count": 45464,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 907.8060095219475,
209
+ "count": 45464,
210
  "is_parallel": true,
211
+ "self": 408.4044104619711,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0018736420001914666,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0005965200002719939,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0012771219999194727,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0012771219999194727
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03432349900003828,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006319849994724791,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.0004138530002819607,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.0004138530002819607
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.031135356000049796,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.031135356000049796
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002142305000234046,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00045947700027682004,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.001682827999957226,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.001682827999957226
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 499.40159905997643,
271
+ "count": 45463,
272
  "is_parallel": true,
273
+ "self": 23.05559838698082,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 13.039904888000365,
277
+ "count": 45463,
278
  "is_parallel": true,
279
+ "self": 13.039904888000365
280
  },
281
  "communicator.exchange": {
282
+ "total": 388.7178397979683,
283
+ "count": 45463,
284
  "is_parallel": true,
285
+ "self": 388.7178397979683
286
  },
287
  "steps_from_proto": {
288
+ "total": 74.58825598702697,
289
+ "count": 45463,
290
  "is_parallel": true,
291
+ "self": 14.302805120039466,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 60.2854508669875,
295
+ "count": 454630,
296
  "is_parallel": true,
297
+ "self": 60.2854508669875
298
  }
299
  }
300
  }
 
305
  }
306
  }
307
  }
308
+ },
309
+ "trainer_advance": {
310
+ "total": 208.9531108069832,
311
+ "count": 45464,
312
+ "self": 1.0602916199259198,
 
 
 
 
 
 
 
 
313
  "children": {
314
+ "process_trajectory": {
315
+ "total": 59.964856461056115,
316
+ "count": 45464,
317
+ "self": 59.82488411605618,
 
318
  "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 0.13997234499993283,
321
+ "count": 1,
322
+ "self": 0.13997234499993283
323
+ }
324
+ }
325
+ },
326
+ "_update_policy": {
327
+ "total": 147.92796272600117,
328
+ "count": 47,
329
+ "self": 113.61383091700554,
330
+ "children": {
331
+ "TorchPPOOptimizer.update": {
332
+ "total": 34.314131808995626,
333
+ "count": 2856,
334
+ "self": 34.314131808995626
 
 
 
 
 
 
 
 
 
 
 
335
  }
336
  }
337
  }
 
339
  }
340
  }
341
  },
342
+ "trainer_threads": {
343
+ "total": 1.4479996934824158e-06,
344
+ "count": 1,
345
+ "self": 1.4479996934824158e-06
346
+ },
347
  "TrainerController._save_models": {
348
+ "total": 0.14580418400009876,
349
  "count": 1,
350
+ "self": 0.0006638550003117416,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.14514032899978702,
354
  "count": 1,
355
+ "self": 0.14514032899978702
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,31 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 12.181818181818182,
8
- "creation_time": 1679674947.930695,
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": 20.363636363636363,
17
- "creation_time": 1679675060.283918,
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": 21.454545454545453,
26
- "creation_time": 1679675172.2147996,
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": 23.181818181818183,
35
- "creation_time": 1679675284.2184937,
36
- "auxillary_file_paths": [
37
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
- ]
39
- },
40
- {
41
- "steps": 200112,
42
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
- "reward": 23.181818181818183,
44
- "creation_time": 1679675284.3977566,
45
- "auxillary_file_paths": [
46
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
  ]
48
  }
49
  ],
50
  "final_checkpoint": {
51
- "steps": 200112,
52
- "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
- "reward": 23.181818181818183,
54
- "creation_time": 1679675284.3977566,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 499976,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.onnx",
7
+ "reward": 25.90909090909091,
8
+ "creation_time": 1679677205.0583572,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-499976.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 500104,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.onnx",
16
+ "reward": 25.90909090909091,
17
+ "creation_time": 1679677205.2193387,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  ]
21
  }
22
  ],
23
  "final_checkpoint": {
24
+ "steps": 500104,
25
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
26
+ "reward": 25.90909090909091,
27
+ "creation_time": 1679677205.2193387,
28
  "auxillary_file_paths": [
29
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-500104.pt"
30
  ]
31
  }
32
  },