igpaub commited on
Commit
5fb0777
1 Parent(s): aa79f12

Second Push

Browse files
SnowballTarget.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c623b15bab220dace42d204e87961ef1380c1a32f1961459a16c9cd6dd23166
3
- size 650646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afc85b21fdc2839f91b2ca5553fcfdf88ec86723cf526e7d165eed507166490
3
+ size 1815958
SnowballTarget/SnowballTarget-1000208.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afc85b21fdc2839f91b2ca5553fcfdf88ec86723cf526e7d165eed507166490
3
+ size 1815958
SnowballTarget/SnowballTarget-1000208.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af6d542419db60abc15be450f8b939cb3ba8db4184c82b511bc7a76a4f2d662
3
+ size 10820582
SnowballTarget/SnowballTarget-599952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5329a73381e98e632d33da3e5c2c7d0ce886ec535eb5f86faa693a19c8768bb
3
+ size 1815958
SnowballTarget/SnowballTarget-599952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d7abc092076f009cb072e4317371c537fb677150144765cfb937fa1b97375d
3
+ size 10820443
SnowballTarget/SnowballTarget-649896.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ebeb11e245b941df7d181646efc81a2ceef6532105acaa90f9b006128c0946
3
+ size 1815958
SnowballTarget/SnowballTarget-649896.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d3e972e5659e0076292780b94e98d836d44fb47fcf04f3cadeb976f35f2323
3
+ size 10820443
SnowballTarget/SnowballTarget-699984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654479426f9c4d37b13f326e2af1a1e112653b2b8c6c25db5e28f20a706d3322
3
+ size 1815958
SnowballTarget/SnowballTarget-699984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f5589a6811b858bccb84bc306f1bc5adb780fb7a8640f5fdf7f3ca5ac16c30
3
+ size 10820443
SnowballTarget/SnowballTarget-749984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228760cd3d9c5f6ee4a7605ff80d6cbe67e28b7b11580a7ecda9e07e0582e25f
3
+ size 1815958
SnowballTarget/SnowballTarget-749984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2433e06f7414614c760cfd0113a2a654c382353a81ba26d948f5fa530fb2deb
3
+ size 10820443
SnowballTarget/SnowballTarget-799880.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c842c56c9f5835d6f572980b27bd4d19a02283dbeb10a76f28bdaff65af9493
3
+ size 1815958
SnowballTarget/SnowballTarget-799880.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09588fb88b518d8ab974facbc6fbdf504e4e8c62f7de26024cf2791f1dcf2dc0
3
+ size 10820443
SnowballTarget/SnowballTarget-849968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947dd5845f9460c8dd0ff0a6a6c5dde33098dd27ce0a6678e25af499d483f07f
3
+ size 1815958
SnowballTarget/SnowballTarget-849968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb4347cd0be7dce219fe1d3086d4e31ecaff4b329f5f0fccce7d32a3b1f9f46
3
+ size 10820443
SnowballTarget/SnowballTarget-899928.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d5a81fcbf81f7e8dc0c97f3601d859c8c2ed64f9a29d5d767b8599f0e34cc6
3
+ size 1815958
SnowballTarget/SnowballTarget-899928.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4f0ae7ad06c6bb3a262b5f608933be2c8688c0bc8af3b09981257576470346
3
+ size 10820443
SnowballTarget/SnowballTarget-949968.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc6f84ce00d03baf7773420f8aeebdd1909c1480efca5db09ecd51600fd362d
3
+ size 1815958
SnowballTarget/SnowballTarget-949968.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7012a7c0797a5c6f5c34354a1c6c2b4d5b85b13abf4264b581fcbd23652930c
3
+ size 10820443
SnowballTarget/SnowballTarget-999952.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afc85b21fdc2839f91b2ca5553fcfdf88ec86723cf526e7d165eed507166490
3
+ size 1815958
SnowballTarget/SnowballTarget-999952.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2da9366191a387bd5acf0a6b2792a432165fdba4adbc693e6a992f4cd9667c1
3
+ size 10820443
SnowballTarget/checkpoint.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9261cd0847889a2ba57b34eeebb2384234789bd3303c994e7b9918008fe01ca
3
- size 3849250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302498aa217a9307f3cdefa89d857836942e05b1ca9e87eb320db86824a7a906
3
+ size 10819618
SnowballTarget/events.out.tfevents.1698231368.0fa4c3474999.3727.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb156503448922f8c541a2cf32cd0f3be879b0eb33460215e3ab89d4d890e7e5
3
+ size 23101
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, "timeout_wait": 60, "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": 512, "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": 1000000, "time_horizon": 128, "summary_freq": 50000, "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, "timeout_wait": 60, "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
@@ -17,7 +17,7 @@ behaviors:
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
@@ -38,9 +38,9 @@ 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
45
  self_play: null
46
  behavioral_cloning: null
@@ -65,7 +65,7 @@ engine_settings:
65
  no_graphics: true
66
  environment_parameters: null
67
  checkpoint_settings:
68
- run_id: SnowballTarget1
69
  initialize_from: null
70
  load_model: false
71
  resume: false
 
17
  checkpoint_interval: 50000
18
  network_settings:
19
  normalize: false
20
+ hidden_units: 512
21
  num_layers: 2
22
  vis_encode_type: simple
23
  memory: null
 
38
  init_path: null
39
  keep_checkpoints: 10
40
  even_checkpoints: false
41
+ max_steps: 1000000
42
+ time_horizon: 128
43
+ summary_freq: 50000
44
  threaded: true
45
  self_play: null
46
  behavioral_cloning: null
 
65
  no_graphics: true
66
  environment_parameters: null
67
  checkpoint_settings:
68
+ run_id: SnowballTarget2
69
  initialize_from: null
70
  load_model: false
71
  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 0.086 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: 0.656869 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 44
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 6.7 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]: 3320 frames, [64.0 KB-128.0 KB]: 2140 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 67.3 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 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 0.077 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: 0.617088 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]: 26832 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 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]: 12418 frames, [8.0 MB-16.0 MB]: 14869 frames
176
  Requested Block Size 16.0 MB
177
+ Peak Block count 2
178
+ Peak Allocated memory 14.4 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 27287 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]: 26250 frames, [64.0 KB-128.0 KB]: 1037 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]: 27287 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]: 27287 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]: 27286 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]: 27287 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]: 27287 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
@@ -2,39 +2,39 @@
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
- "value": 0.9394565224647522,
6
- "min": 0.9141441583633423,
7
- "max": 2.8565824031829834,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
- "value": 8969.9306640625,
12
- "min": 8969.9306640625,
13
- "max": 29285.681640625,
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": 11.45400619506836,
30
- "min": 0.3070013225078583,
31
- "max": 11.45400619506836,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
- "value": 2233.53125,
36
- "min": 59.558258056640625,
37
- "max": 2303.4033203125,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,93 +44,93 @@
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": 0.06720656596064822,
54
- "min": 0.06381262132188069,
55
- "max": 0.07530971806480402,
56
  "count": 20
57
  },
58
  "SnowballTarget.Losses.PolicyLoss.sum": {
59
- "value": 0.2688262638425929,
60
- "min": 0.25525048528752275,
61
- "max": 0.36782232005526905,
62
  "count": 20
63
  },
64
  "SnowballTarget.Losses.ValueLoss.mean": {
65
- "value": 0.215917447399275,
66
- "min": 0.12496637004455002,
67
- "max": 0.26474717008132564,
68
  "count": 20
69
  },
70
  "SnowballTarget.Losses.ValueLoss.sum": {
71
- "value": 0.8636697895971,
72
- "min": 0.4998654801782001,
73
- "max": 1.3237358504066281,
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": 22.681818181818183,
114
- "min": 3.3181818181818183,
115
- "max": 22.927272727272726,
116
- "count": 20
117
- },
118
- "SnowballTarget.Environment.CumulativeReward.sum": {
119
- "value": 998.0,
120
- "min": 146.0,
121
- "max": 1261.0,
122
- "count": 20
123
- },
124
- "SnowballTarget.Policy.ExtrinsicReward.mean": {
125
- "value": 22.681818181818183,
126
- "min": 3.3181818181818183,
127
- "max": 22.927272727272726,
128
- "count": 20
129
- },
130
- "SnowballTarget.Policy.ExtrinsicReward.sum": {
131
- "value": 998.0,
132
- "min": 146.0,
133
- "max": 1261.0,
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
- "start_time_seconds": "1698225825",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
- "end_time_seconds": "1698226313"
160
  },
161
- "total": 488.13565355700007,
162
  "count": 1,
163
- "self": 0.4345231900000499,
164
  "children": {
165
  "run_training.setup": {
166
- "total": 0.04804301399997257,
167
  "count": 1,
168
- "self": 0.04804301399997257
169
  },
170
  "TrainerController.start_learning": {
171
- "total": 487.65308735300005,
172
  "count": 1,
173
- "self": 0.5719399940015819,
174
  "children": {
175
  "TrainerController._reset_env": {
176
- "total": 9.068871303999913,
177
  "count": 1,
178
- "self": 9.068871303999913
179
  },
180
  "TrainerController.advance": {
181
- "total": 477.9206781389986,
182
- "count": 18199,
183
- "self": 0.28348906800567875,
184
  "children": {
185
  "env_step": {
186
- "total": 477.6371890709929,
187
- "count": 18199,
188
- "self": 327.7294423999896,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
- "total": 149.62392567400752,
192
- "count": 18199,
193
- "self": 1.4933443199956855,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
- "total": 148.13058135401184,
197
- "count": 18199,
198
- "self": 148.13058135401184
199
  }
200
  }
201
  },
202
  "workers": {
203
- "total": 0.2838209969958143,
204
- "count": 18199,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
- "total": 486.33171994800125,
209
- "count": 18199,
210
  "is_parallel": true,
211
- "self": 238.79206083402175,
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": 0.0068975640000417116,
221
  "count": 1,
222
  "is_parallel": true,
223
- "self": 0.004877579000094556,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
- "total": 0.0020199849999471553,
227
  "count": 10,
228
  "is_parallel": true,
229
- "self": 0.0020199849999471553
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
- "total": 0.035607216000016706,
235
  "count": 1,
236
  "is_parallel": true,
237
- "self": 0.0006440709998969396,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
- "total": 0.00032739499999934196,
241
  "count": 1,
242
  "is_parallel": true,
243
- "self": 0.00032739499999934196
244
  },
245
  "communicator.exchange": {
246
- "total": 0.03265452800008006,
247
  "count": 1,
248
  "is_parallel": true,
249
- "self": 0.03265452800008006
250
  },
251
  "steps_from_proto": {
252
- "total": 0.0019812220000403613,
253
  "count": 1,
254
  "is_parallel": true,
255
- "self": 0.0003665650001494214,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
- "total": 0.00161465699989094,
259
  "count": 10,
260
  "is_parallel": true,
261
- "self": 0.00161465699989094
262
  }
263
  }
264
  }
@@ -267,34 +267,34 @@
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
- "total": 247.5396591139795,
271
- "count": 18198,
272
  "is_parallel": true,
273
- "self": 11.20132669798727,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
- "total": 5.652011376013661,
277
- "count": 18198,
278
  "is_parallel": true,
279
- "self": 5.652011376013661
280
  },
281
  "communicator.exchange": {
282
- "total": 195.0709025789905,
283
- "count": 18198,
284
  "is_parallel": true,
285
- "self": 195.0709025789905
286
  },
287
  "steps_from_proto": {
288
- "total": 35.61541846098805,
289
- "count": 18198,
290
  "is_parallel": true,
291
- "self": 6.659154703984541,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
- "total": 28.956263757003512,
295
- "count": 181980,
296
  "is_parallel": true,
297
- "self": 28.956263757003512
298
  }
299
  }
300
  }
@@ -309,9 +309,9 @@
309
  }
310
  },
311
  "trainer_threads": {
312
- "total": 0.00011800400011452439,
313
  "count": 1,
314
- "self": 0.00011800400011452439,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
@@ -320,36 +320,36 @@
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
- "total": 473.85948956696063,
324
- "count": 487821,
325
  "is_parallel": true,
326
- "self": 10.715996395939555,
327
  "children": {
328
  "process_trajectory": {
329
- "total": 268.5420727360215,
330
- "count": 487821,
331
  "is_parallel": true,
332
- "self": 267.84766477002165,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
- "total": 0.6944079659998579,
336
- "count": 4,
337
  "is_parallel": true,
338
- "self": 0.6944079659998579
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
- "total": 194.60142043499957,
344
- "count": 90,
345
  "is_parallel": true,
346
- "self": 60.966182846988545,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
- "total": 133.63523758801102,
350
- "count": 4587,
351
  "is_parallel": true,
352
- "self": 133.63523758801102
353
  }
354
  }
355
  }
@@ -360,14 +360,14 @@
360
  }
361
  },
362
  "TrainerController._save_models": {
363
- "total": 0.09147991199984062,
364
  "count": 1,
365
- "self": 0.0008560419998957514,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
- "total": 0.09062386999994487,
369
  "count": 1,
370
- "self": 0.09062386999994487
371
  }
372
  }
373
  }
 
2
  "name": "root",
3
  "gauges": {
4
  "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.5860854387283325,
6
+ "min": 0.5860854387283325,
7
+ "max": 2.443842887878418,
8
  "count": 20
9
  },
10
  "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 29282.001953125,
12
+ "min": 29282.001953125,
13
+ "max": 123658.453125,
14
  "count": 20
15
  },
16
  "SnowballTarget.Step.mean": {
17
+ "value": 999952.0,
18
+ "min": 49952.0,
19
+ "max": 999952.0,
20
  "count": 20
21
  },
22
  "SnowballTarget.Step.sum": {
23
+ "value": 999952.0,
24
+ "min": 49952.0,
25
+ "max": 999952.0,
26
  "count": 20
27
  },
28
  "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 14.130938529968262,
30
+ "min": 3.2179858684539795,
31
+ "max": 14.170147895812988,
32
  "count": 20
33
  },
34
  "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 7051.33837890625,
36
+ "min": 1599.3389892578125,
37
+ "max": 7113.4140625,
38
  "count": 20
39
  },
40
  "SnowballTarget.Environment.EpisodeLength.mean": {
 
44
  "count": 20
45
  },
46
  "SnowballTarget.Environment.EpisodeLength.sum": {
47
+ "value": 48158.0,
48
+ "min": 48158.0,
49
+ "max": 50347.0,
50
+ "count": 20
51
+ },
52
+ "SnowballTarget.Environment.CumulativeReward.mean": {
53
+ "value": 27.798387096774192,
54
+ "min": 10.15983606557377,
55
+ "max": 27.8300395256917,
56
+ "count": 20
57
+ },
58
+ "SnowballTarget.Environment.CumulativeReward.sum": {
59
+ "value": 6894.0,
60
+ "min": 2479.0,
61
+ "max": 7041.0,
62
+ "count": 20
63
+ },
64
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
65
+ "value": 27.798387096774192,
66
+ "min": 10.15983606557377,
67
+ "max": 27.8300395256917,
68
+ "count": 20
69
+ },
70
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
71
+ "value": 6894.0,
72
+ "min": 2479.0,
73
+ "max": 7041.0,
74
  "count": 20
75
  },
76
  "SnowballTarget.Losses.PolicyLoss.mean": {
77
+ "value": 0.07071791908982689,
78
+ "min": 0.06703672302408809,
79
+ "max": 0.07201141945276286,
80
  "count": 20
81
  },
82
  "SnowballTarget.Losses.PolicyLoss.sum": {
83
+ "value": 1.6265121390660184,
84
+ "min": 1.474807906529938,
85
+ "max": 1.6562626474135458,
86
  "count": 20
87
  },
88
  "SnowballTarget.Losses.ValueLoss.mean": {
89
+ "value": 0.17576968430431092,
90
+ "min": 0.1658779936004986,
91
+ "max": 0.2771722643881503,
92
  "count": 20
93
  },
94
  "SnowballTarget.Losses.ValueLoss.sum": {
95
+ "value": 4.042702738999151,
96
+ "min": 3.8151938528114675,
97
+ "max": 6.374962080927457,
98
  "count": 20
99
  },
100
  "SnowballTarget.Policy.LearningRate.mean": {
101
+ "value": 7.620097460000001e-06,
102
+ "min": 7.620097460000001e-06,
103
+ "max": 0.0002924109843478546,
104
  "count": 20
105
  },
106
  "SnowballTarget.Policy.LearningRate.sum": {
107
+ "value": 0.00017526224158,
108
+ "min": 0.00017526224158,
109
+ "max": 0.006433041655652801,
110
  "count": 20
111
  },
112
  "SnowballTarget.Policy.Epsilon.mean": {
113
+ "value": 0.10254,
114
+ "min": 0.10254,
115
+ "max": 0.1974703272727273,
116
  "count": 20
117
  },
118
  "SnowballTarget.Policy.Epsilon.sum": {
119
+ "value": 2.35842,
120
+ "min": 2.35842,
121
+ "max": 4.427960000000001,
122
  "count": 20
123
  },
124
  "SnowballTarget.Policy.Beta.mean": {
125
+ "value": 0.000136746,
126
+ "min": 0.000136746,
127
+ "max": 0.004873769330909091,
128
  "count": 20
129
  },
130
  "SnowballTarget.Policy.Beta.sum": {
131
+ "value": 0.0031451580000000003,
132
+ "min": 0.0031451580000000003,
133
+ "max": 0.10722292527999999,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  "count": 20
135
  },
136
  "SnowballTarget.IsTraining.mean": {
 
148
  },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1698231368",
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": "1.1.0.dev0",
155
  "mlagents_envs_version": "1.1.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.1.0+cu118",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1698233609"
160
  },
161
+ "total": 2241.1600546160003,
162
  "count": 1,
163
+ "self": 0.4240094830001908,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.042658243000005314,
167
  "count": 1,
168
+ "self": 0.042658243000005314
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 2240.69338689,
172
  "count": 1,
173
+ "self": 2.80471784100655,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 3.1852731500000573,
177
  "count": 1,
178
+ "self": 3.1852731500000573
179
  },
180
  "TrainerController.advance": {
181
+ "total": 2234.5915062999934,
182
+ "count": 90954,
183
+ "self": 1.3369565009556936,
184
  "children": {
185
  "env_step": {
186
+ "total": 2233.2545497990377,
187
+ "count": 90954,
188
+ "self": 1437.3404762530213,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 794.511444212965,
192
+ "count": 90954,
193
+ "self": 7.143909519008162,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 787.3675346939568,
197
+ "count": 90954,
198
+ "self": 787.3675346939568
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 1.4026293330514363,
204
+ "count": 90954,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 2234.3299840999957,
209
+ "count": 90954,
210
  "is_parallel": true,
211
+ "self": 1030.1527709440015,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.0020364339999332515,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.0006503330001805807,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0013861009997526708,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0013861009997526708
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.0351438180000514,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0006059190000087256,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.000343800999985433,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.000343800999985433
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.0323127190000605,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.0323127190000605
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0018813789999967412,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.000367557000117813,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0015138219998789282,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0015138219998789282
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 1204.1772131559942,
271
+ "count": 90953,
272
  "is_parallel": true,
273
+ "self": 52.74599389899549,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 27.691112145988882,
277
+ "count": 90953,
278
  "is_parallel": true,
279
+ "self": 27.691112145988882
280
  },
281
  "communicator.exchange": {
282
+ "total": 948.1140495010205,
283
+ "count": 90953,
284
  "is_parallel": true,
285
+ "self": 948.1140495010205
286
  },
287
  "steps_from_proto": {
288
+ "total": 175.62605760998918,
289
+ "count": 90953,
290
  "is_parallel": true,
291
+ "self": 32.82275263505085,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 142.80330497493833,
295
+ "count": 909530,
296
  "is_parallel": true,
297
+ "self": 142.80330497493833
298
  }
299
  }
300
  }
 
309
  }
310
  },
311
  "trainer_threads": {
312
+ "total": 0.00027903399995921063,
313
  "count": 1,
314
+ "self": 0.00027903399995921063,
315
  "children": {
316
  "thread_root": {
317
  "total": 0.0,
 
320
  "self": 0.0,
321
  "children": {
322
  "trainer_advance": {
323
+ "total": 2221.978957164012,
324
+ "count": 1644593,
325
  "is_parallel": true,
326
+ "self": 35.98496506884294,
327
  "children": {
328
  "process_trajectory": {
329
+ "total": 932.611493342173,
330
+ "count": 1644593,
331
  "is_parallel": true,
332
+ "self": 928.8194726101746,
333
  "children": {
334
  "RLTrainer._checkpoint": {
335
+ "total": 3.792020731998491,
336
+ "count": 20,
337
  "is_parallel": true,
338
+ "self": 3.792020731998491
339
  }
340
  }
341
  },
342
  "_update_policy": {
343
+ "total": 1253.382498752996,
344
+ "count": 454,
345
  "is_parallel": true,
346
+ "self": 324.37970300498364,
347
  "children": {
348
  "TorchPPOOptimizer.update": {
349
+ "total": 929.0027957480124,
350
+ "count": 23151,
351
  "is_parallel": true,
352
+ "self": 929.0027957480124
353
  }
354
  }
355
  }
 
360
  }
361
  },
362
  "TrainerController._save_models": {
363
+ "total": 0.11161056500031918,
364
  "count": 1,
365
+ "self": 0.0015727760005574964,
366
  "children": {
367
  "RLTrainer._checkpoint": {
368
+ "total": 0.11003778899976169,
369
  "count": 1,
370
+ "self": 0.11003778899976169
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": 13.727272727272727,
8
- "creation_time": 1698225956.00584,
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": 16.90909090909091,
17
- "creation_time": 1698226075.252297,
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": 20.454545454545453,
26
- "creation_time": 1698226195.1428246,
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": 22.90909090909091,
35
- "creation_time": 1698226312.8405104,
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": 22.90909090909091,
44
- "creation_time": 1698226312.9550734,
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": 22.90909090909091,
54
- "creation_time": 1698226312.9550734,
55
  "auxillary_file_paths": [
56
- "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
  ]
58
  }
59
  },
 
2
  "SnowballTarget": {
3
  "checkpoints": [
4
  {
5
+ "steps": 599952,
6
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-599952.onnx",
7
+ "reward": 28.0,
8
+ "creation_time": 1698232720.478212,
9
  "auxillary_file_paths": [
10
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-599952.pt"
11
  ]
12
  },
13
  {
14
+ "steps": 649896,
15
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-649896.onnx",
16
+ "reward": null,
17
+ "creation_time": 1698232833.2968547,
18
  "auxillary_file_paths": [
19
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-649896.pt"
20
  ]
21
  },
22
  {
23
+ "steps": 699984,
24
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-699984.onnx",
25
+ "reward": null,
26
+ "creation_time": 1698232945.6497917,
27
  "auxillary_file_paths": [
28
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-699984.pt"
29
  ]
30
  },
31
  {
32
+ "steps": 749984,
33
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-749984.onnx",
34
+ "reward": 28.0,
35
+ "creation_time": 1698233055.3665125,
36
  "auxillary_file_paths": [
37
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-749984.pt"
38
  ]
39
  },
40
  {
41
+ "steps": 799880,
42
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-799880.onnx",
43
+ "reward": null,
44
+ "creation_time": 1698233165.3728077,
45
  "auxillary_file_paths": [
46
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-799880.pt"
47
+ ]
48
+ },
49
+ {
50
+ "steps": 849968,
51
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-849968.onnx",
52
+ "reward": null,
53
+ "creation_time": 1698233277.524831,
54
+ "auxillary_file_paths": [
55
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-849968.pt"
56
+ ]
57
+ },
58
+ {
59
+ "steps": 899928,
60
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-899928.onnx",
61
+ "reward": null,
62
+ "creation_time": 1698233389.957055,
63
+ "auxillary_file_paths": [
64
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-899928.pt"
65
+ ]
66
+ },
67
+ {
68
+ "steps": 949968,
69
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-949968.onnx",
70
+ "reward": 26.8,
71
+ "creation_time": 1698233498.195285,
72
+ "auxillary_file_paths": [
73
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-949968.pt"
74
+ ]
75
+ },
76
+ {
77
+ "steps": 999952,
78
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.onnx",
79
+ "reward": null,
80
+ "creation_time": 1698233608.857729,
81
+ "auxillary_file_paths": [
82
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.pt"
83
+ ]
84
+ },
85
+ {
86
+ "steps": 1000208,
87
+ "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.onnx",
88
+ "reward": null,
89
+ "creation_time": 1698233608.9966645,
90
+ "auxillary_file_paths": [
91
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.pt"
92
  ]
93
  }
94
  ],
95
  "final_checkpoint": {
96
+ "steps": 1000208,
97
+ "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
98
+ "reward": null,
99
+ "creation_time": 1698233608.9966645,
100
  "auxillary_file_paths": [
101
+ "results/SnowballTarget2/SnowballTarget/SnowballTarget-1000208.pt"
102
  ]
103
  }
104
  },