AMI0x commited on
Commit
68b7591
β€’
1 Parent(s): 8b4afcc

500K Step Trainning Agent

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e059fbb82d6d65682070582fe57e21d79692a2eb236dafe47590c915842d97bb
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
3
  size 646532
SnowballTarget/{SnowballTarget-149984.onnx β†’ SnowballTarget-249984.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa68ac8f2f4758d9e81a993ba1e65a814a03575e2c5b0c372f7261130951809e
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20fd838dce7ccc00ecebb325bfe4dc8d2fd50aa9757727bf606b14e332fe16f
3
  size 646532
SnowballTarget/{SnowballTarget-99960.pt β†’ SnowballTarget-249984.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e65fdc8f305e4e52e0629727338f19104ad33e3d0cea40618a79de85b8d21ea
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd196c59bfcaf10abdce372602c80e34807aa6105d25366d3ea086d99c0dcc3
3
  size 3843968
SnowballTarget/{SnowballTarget-99960.onnx β†’ SnowballTarget-299944.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a219b4751c8b3666c5ffd16021b23750330e5b89c1302c76cd5133000107cf23
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a2a116ac1b4180e88392dc7c247e19c5bd35edd82e25a514a4e5269a101dfc
3
  size 646532
SnowballTarget/{SnowballTarget-149984.pt β†’ SnowballTarget-299944.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a16b977bd2ff2478e32b096dabfdd0e21f96e3368dc3ebceb42e7258c96d3f59
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90e748bafd7c33e61b86715ee036af952f4aab9011c227d79a280eedd25affb
3
  size 3843968
SnowballTarget/{SnowballTarget-49936.onnx β†’ SnowballTarget-349968.onnx} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a87b5314ad5661b1fafd0ae2b517fa42f4f2e09376c97a64c8b48a53d55ff37
3
  size 646532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe94ba2022928a9a447112989963c9b4109dabe655bdf29d2be90ced1748aaf9
3
  size 646532
SnowballTarget/{SnowballTarget-49936.pt β†’ SnowballTarget-349968.pt} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63fe7551bd6242c77d954d699b6d4de1340e8ce66fa45ecb6a7f1d4e37b42c28
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94782d445a7841fc969622976517e07f35f5678b2fcb1d80759a438bf189ee01
3
  size 3843968
SnowballTarget/SnowballTarget-399968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c86a00fdcd77fb128b3cd1cedef1bd5f105aeaf03d7a4e83d08093f25994ce8
3
+ size 646532
SnowballTarget/SnowballTarget-399968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c2114a94c41e86c4588bb71a5dbcdce200fe718221373079efa003268f79ff
3
+ size 3843968
SnowballTarget/SnowballTarget-449992.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51b5577ab81a166da9030a3bcef0bde6867d2ca47650c2eec50b7919ad01755
3
+ size 646532
SnowballTarget/SnowballTarget-449992.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd3ca2d4b34d8af8253fb45c32dc9d605e3ab062271306dba009a44de5ddaff
3
+ size 3843968
SnowballTarget/SnowballTarget-499952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
3
+ size 646532
SnowballTarget/SnowballTarget-499952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a2fc614bf1cf2476730424c3a93a8dfe640e2d40a9e9101e5d26d96d635ec4
3
+ size 3843968
SnowballTarget/SnowballTarget-500016.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
3
+ size 646532
SnowballTarget/SnowballTarget-500016.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ebbf2f7707aef1728f0e45066d410bc2ffbe741a2d52a1225754ea3c58a15
3
+ size 3843968
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77154e5e1280e87d4479860e435a180c030e691119279c7ef73cf327a934a081
3
  size 3843968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ebbf2f7707aef1728f0e45066d410bc2ffbe741a2d52a1225754ea3c58a15
3
  size 3843968
SnowballTarget/events.out.tfevents.1682358087.a18477c96443.5751.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414b7e33997e9b6aa564d7e77ba721352b775084f56c6c9673df128af78ce82f
3
+ size 1114
SnowballTarget/events.out.tfevents.1682358145.a18477c96443.6061.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6283f3782d217de82e84cc41740ace910c697bb93a19d1fb24b9656dd01a0b
3
+ size 25806
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -38,7 +38,7 @@ behaviors:
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
@@ -67,7 +67,7 @@ checkpoint_settings:
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
- resume: false
71
  force: false
72
  train_model: false
73
  inference: false
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 500000
42
  time_horizon: 64
43
  summary_freq: 10000
44
  threaded: true
 
67
  run_id: SnowballTarget1
68
  initialize_from: null
69
  load_model: false
70
+ resume: true
71
  force: false
72
  train_model: false
73
  inference: 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 0.132 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: 1.010365 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]: 5368 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 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]: 5460 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]: 5460 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]: 4218 frames, [64.0 KB-128.0 KB]: 1242 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]: 5460 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]: 5460 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]: 5459 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]: 5460 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]: 5460 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 0.088 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: 0.761045 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]: 8047 frames, [16.0 KB-32.0 KB]: 136 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 36
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]: 8184 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 7.3 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 8184 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]: 7212 frames, [64.0 KB-128.0 KB]: 972 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]: 8184 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]: 8184 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]: 8183 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]: 8184 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]: 8184 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": 0.9684804677963257,
6
- "min": 0.9665554165840149,
7
- "max": 2.8610684871673584,
8
- "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 9247.0517578125,
12
- "min": 9247.0517578125,
13
- "max": 29331.673828125,
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": 11.88376235961914,
30
- "min": 0.42129021883010864,
31
- "max": 11.88376235961914,
32
- "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2317.333740234375,
36
- "min": 81.73030090332031,
37
- "max": 2420.123046875,
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": 0.06678682855386332,
54
- "min": 0.06264865814648823,
55
- "max": 0.07348273087785963,
56
- "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2671473142154533,
60
- "min": 0.25059463258595294,
61
- "max": 0.35259857336573347,
62
- "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.18828831204012328,
66
- "min": 0.12193425533854788,
67
- "max": 0.2692366852333733,
68
- "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.7531532481604931,
72
- "min": 0.4877370213541915,
73
- "max": 1.3165682127662732,
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": 23.34090909090909,
114
- "min": 3.5,
115
- "max": 23.436363636363637,
116
- "count": 20
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 1027.0,
120
- "min": 154.0,
121
- "max": 1289.0,
122
- "count": 20
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 23.34090909090909,
126
- "min": 3.5,
127
- "max": 23.436363636363637,
128
- "count": 20
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 1027.0,
132
- "min": 154.0,
133
- "max": 1289.0,
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": "1682357155",
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": "1682357672"
160
  },
161
- "total": 516.7167141909999,
162
  "count": 1,
163
- "self": 0.48507005299984485,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.20040222800002994,
167
  "count": 1,
168
- "self": 0.20040222800002994
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 516.0312419100001,
172
  "count": 1,
173
- "self": 0.6946911010028316,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 6.026232261000018,
177
  "count": 1,
178
- "self": 6.026232261000018
179
  },
180
  "TrainerController.advance": {
181
- "total": 509.17044381799707,
182
- "count": 18200,
183
- "self": 0.36501226900202255,
184
  "children": {
185
  "env_step": {
186
- "total": 508.80543154899505,
187
- "count": 18200,
188
- "self": 372.9479452349953,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 135.518353045999,
192
- "count": 18200,
193
- "self": 1.9585550909902736,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 133.55979795500872,
197
- "count": 18200,
198
- "self": 133.55979795500872
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.33913326800075083,
204
- "count": 18200,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 514.3362900880015,
209
- "count": 18200,
210
  "is_parallel": true,
211
- "self": 233.94241602600715,
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": 0.006583159000001615,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.0042210009999053,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.002362158000096315,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.002362158000096315
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.03869263500001807,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006917510000334914,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.0003822740000032354,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.0003822740000032354
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03551086900000655,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03551086900000655
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0021077409999747942,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.00041510799997013237,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.0016926330000046619,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.0016926330000046619
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 280.3938740619944,
271
- "count": 18199,
272
  "is_parallel": true,
273
- "self": 11.282627253996395,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.999943185995505,
277
- "count": 18199,
278
  "is_parallel": true,
279
- "self": 5.999943185995505
280
  },
281
  "communicator.exchange": {
282
- "total": 227.30850375700072,
283
- "count": 18199,
284
  "is_parallel": true,
285
- "self": 227.30850375700072
286
  },
287
  "steps_from_proto": {
288
- "total": 35.80279986500176,
289
- "count": 18199,
290
  "is_parallel": true,
291
- "self": 7.392354915014039,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.41044494998772,
295
- "count": 181990,
296
  "is_parallel": true,
297
- "self": 28.41044494998772
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 3.7070000075800635e-05,
313
  "count": 1,
314
- "self": 3.7070000075800635e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 504.75749249595043,
324
- "count": 469320,
325
  "is_parallel": true,
326
- "self": 12.290094086947477,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 281.2713377250029,
330
- "count": 469320,
331
  "is_parallel": true,
332
- "self": 280.0705311930031,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 1.200806531999831,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 1.200806531999831
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 211.19606068400003,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 75.00589306599863,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 136.1901676180014,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 136.1901676180014
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.13983766000001197,
364
  "count": 1,
365
- "self": 0.0010233990000187987,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.13881426099999317,
369
  "count": 1,
370
- "self": 0.13881426099999317
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.6655184626579285,
6
+ "min": 0.617180585861206,
7
+ "max": 0.9582071900367737,
8
+ "count": 30
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 6420.2568359375,
12
+ "min": 5858.89501953125,
13
+ "max": 9813.0,
14
+ "count": 30
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 499952.0,
18
+ "min": 209936.0,
19
+ "max": 499952.0,
20
+ "count": 30
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 499952.0,
24
+ "min": 209936.0,
25
+ "max": 499952.0,
26
+ "count": 30
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.066350936889648,
30
+ "min": 11.845895767211914,
31
+ "max": 13.117155075073242,
32
+ "count": 30
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 2665.53564453125,
36
+ "min": 2291.858642578125,
37
+ "max": 2673.39697265625,
38
+ "count": 30
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
41
  "value": 199.0,
42
  "min": 199.0,
43
  "max": 199.0,
44
+ "count": 30
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 10945.0,
48
  "min": 8756.0,
49
  "max": 10945.0,
50
+ "count": 30
51
  },
52
  "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.06782656824045048,
54
+ "min": 0.061637699475635174,
55
+ "max": 0.07558078284441852,
56
+ "count": 30
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.3391328412022524,
60
+ "min": 0.2465507979025407,
61
+ "max": 0.3779039142220926,
62
+ "count": 30
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.16957302873625474,
66
+ "min": 0.15925985475381216,
67
+ "max": 0.19927547601800338,
68
+ "count": 30
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.8478651436812737,
72
+ "min": 0.6766528339654792,
73
+ "max": 0.9778521423246346,
74
+ "count": 30
75
  },
76
  "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.1056989647999945e-06,
78
+ "min": 3.1056989647999945e-06,
79
+ "max": 0.00017668564110480002,
80
+ "count": 30
81
  },
82
  "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 1.5528494823999972e-05,
84
+ "min": 1.5528494823999972e-05,
85
+ "max": 0.000853728215424,
86
+ "count": 30
87
  },
88
  "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.10103520000000002,
90
+ "min": 0.10103520000000002,
91
+ "max": 0.15889520000000001,
92
+ "count": 30
93
  },
94
  "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.5051760000000001,
96
+ "min": 0.4120608,
97
+ "max": 0.7845760000000002,
98
+ "count": 30
99
  },
100
  "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.165647999999992e-05,
102
+ "min": 6.165647999999992e-05,
103
+ "max": 0.002948870480000001,
104
+ "count": 30
105
  },
106
  "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 0.0003082823999999996,
108
+ "min": 0.0003082823999999996,
109
+ "max": 0.0142503424,
110
+ "count": 30
111
  },
112
  "SnowballTarget.Environment.CumulativeReward.mean": {
113
+ "value": 26.01818181818182,
114
+ "min": 23.272727272727273,
115
+ "max": 26.01818181818182,
116
+ "count": 30
117
  },
118
  "SnowballTarget.Environment.CumulativeReward.sum": {
119
+ "value": 1431.0,
120
+ "min": 1033.0,
121
+ "max": 1431.0,
122
+ "count": 30
123
  },
124
  "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
+ "value": 26.01818181818182,
126
+ "min": 23.272727272727273,
127
+ "max": 26.01818181818182,
128
+ "count": 30
129
  },
130
  "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
+ "value": 1431.0,
132
+ "min": 1033.0,
133
+ "max": 1431.0,
134
+ "count": 30
135
  },
136
  "SnowballTarget.IsTraining.mean": {
137
  "value": 1.0,
138
  "min": 1.0,
139
  "max": 1.0,
140
+ "count": 30
141
  },
142
  "SnowballTarget.IsTraining.sum": {
143
  "value": 1.0,
144
  "min": 1.0,
145
  "max": 1.0,
146
+ "count": 30
147
  }
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1682358144",
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 --resume",
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": "1682358916"
160
  },
161
+ "total": 771.782464225,
162
  "count": 1,
163
+ "self": 0.42619025900012275,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.12090538699999342,
167
  "count": 1,
168
+ "self": 0.12090538699999342
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 771.2353685789999,
172
  "count": 1,
173
+ "self": 0.9749921189966244,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.78697043499983,
177
  "count": 1,
178
+ "self": 3.78697043499983
179
  },
180
  "TrainerController.advance": {
181
+ "total": 766.3194630150033,
182
+ "count": 27277,
183
+ "self": 0.4873033090048011,
184
  "children": {
185
  "env_step": {
186
+ "total": 765.8321597059985,
187
+ "count": 27277,
188
+ "self": 560.3379320839692,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 205.00281449902013,
192
+ "count": 27277,
193
+ "self": 2.854428264005719,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 202.1483862350144,
197
+ "count": 27277,
198
+ "self": 202.1483862350144
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.4914131230091243,
204
+ "count": 27277,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 768.7621924489877,
209
+ "count": 27277,
210
  "is_parallel": true,
211
+ "self": 348.3900992389922,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0020266750000246248,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000663230999634834,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013634440003897907,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013634440003897907
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03653779000001123,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.000623500000074273,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00035205000017413113,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00035205000017413113
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.033465286999899035,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.033465286999899035
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.002096952999863788,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00044193199937581085,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016550210004879773,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016550210004879773
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 420.37209320999546,
271
+ "count": 27276,
272
  "is_parallel": true,
273
+ "self": 16.572916214011002,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 9.062697829995159,
277
+ "count": 27276,
278
  "is_parallel": true,
279
+ "self": 9.062697829995159
280
  },
281
  "communicator.exchange": {
282
+ "total": 341.0861296830112,
283
+ "count": 27276,
284
  "is_parallel": true,
285
+ "self": 341.0861296830112
286
  },
287
  "steps_from_proto": {
288
+ "total": 53.65034948297807,
289
+ "count": 27276,
290
  "is_parallel": true,
291
+ "self": 11.027815503917736,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 42.622533979060336,
295
+ "count": 272760,
296
  "is_parallel": true,
297
+ "self": 42.622533979060336
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 6.132499993327656e-05,
313
  "count": 1,
314
+ "self": 6.132499993327656e-05,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 760.2009560629922,
324
+ "count": 695956,
325
  "is_parallel": true,
326
+ "self": 18.176444329957803,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 419.70010413003524,
330
+ "count": 695956,
331
  "is_parallel": true,
332
+ "self": 417.8537270100355,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 1.8463771199997154,
336
+ "count": 6,
337
  "is_parallel": true,
338
+ "self": 1.8463771199997154
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 322.32440760299914,
344
+ "count": 136,
345
  "is_parallel": true,
346
+ "self": 115.05255194398,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 207.27185565901914,
350
+ "count": 6930,
351
  "is_parallel": true,
352
+ "self": 207.27185565901914
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.15388168500021493,
364
  "count": 1,
365
+ "self": 0.002220347000275069,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.15166133799993986,
369
  "count": 1,
370
+ "self": 0.15166133799993986
371
  }
372
  }
373
  }
run_logs/training_status.json CHANGED
@@ -2,58 +2,103 @@
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
- "steps": 49936,
6
- "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
- "reward": 13.363636363636363,
8
- "creation_time": 1682357288.7593153,
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": 20.0,
17
- "creation_time": 1682357417.0077095,
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": 21.90909090909091,
26
- "creation_time": 1682357545.581245,
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": 22.363636363636363,
35
- "creation_time": 1682357671.458759,
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": 22.363636363636363,
44
- "creation_time": 1682357671.6289852,
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": 22.363636363636363,
54
- "creation_time": 1682357671.6289852,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 199984,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
7
+ "reward": 22.363636363636363,
8
+ "creation_time": 1682357671.458759,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 200112,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
16
+ "reward": 22.363636363636363,
17
+ "creation_time": 1682357671.6289852,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 200112,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
25
+ "reward": null,
26
+ "creation_time": 1682358091.1392028,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 249984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
34
+ "reward": 24.0,
35
+ "creation_time": 1682358278.3226972,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 299944,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
43
+ "reward": 24.363636363636363,
44
+ "creation_time": 1682358406.4953222,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 349968,
51
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
52
+ "reward": 25.454545454545453,
53
+ "creation_time": 1682358535.671669,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 399968,
60
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
61
+ "reward": 24.181818181818183,
62
+ "creation_time": 1682358665.1557727,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 449992,
69
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
70
+ "reward": 24.727272727272727,
71
+ "creation_time": 1682358791.0211678,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 499952,
78
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
79
+ "reward": 26.90909090909091,
80
+ "creation_time": 1682358915.5257006,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 500016,
87
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
88
+ "reward": 26.90909090909091,
89
+ "creation_time": 1682358915.7000394,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 500016,
97
  "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
98
+ "reward": 26.90909090909091,
99
+ "creation_time": 1682358915.7000394,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
102
  ]
103
  }
104
  },