Second Push
Browse files- SnowballTarget.onnx +1 -1
- SnowballTarget/SnowballTarget-149984.onnx +1 -1
- SnowballTarget/SnowballTarget-149984.pt +1 -1
- SnowballTarget/SnowballTarget-199984.onnx +1 -1
- SnowballTarget/SnowballTarget-199984.pt +1 -1
- SnowballTarget/SnowballTarget-200112.onnx +1 -1
- SnowballTarget/SnowballTarget-200112.pt +1 -1
- SnowballTarget/SnowballTarget-49936.onnx +1 -1
- SnowballTarget/SnowballTarget-49936.pt +1 -1
- SnowballTarget/SnowballTarget-99960.onnx +1 -1
- SnowballTarget/SnowballTarget-99960.pt +1 -1
- SnowballTarget/checkpoint.pt +1 -1
- SnowballTarget/events.out.tfevents.1697022380.429c7995e803.804.0 +3 -0
- config.json +1 -1
- configuration.yaml +1 -1
- run_logs/Player-0.log +17 -17
- run_logs/timers.json +112 -112
- run_logs/training_status.json +24 -24
SnowballTarget.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03ee03e47e4fa5dab20cfe0849a6ff1877df60d2cdefa0b35559ea169ec0562
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-149984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cb71a61db11e189f5730d6213cc8f8f3bd546e2f97fb5ebca3d83bf4a6dea70
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-149984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849614
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0840b882412761804c3efe2513c4f857d6fe6f0b5bee0c0828fe61b5e635d75
|
| 3 |
size 3849614
|
SnowballTarget/SnowballTarget-199984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03ee03e47e4fa5dab20cfe0849a6ff1877df60d2cdefa0b35559ea169ec0562
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-199984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849614
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a7d69796004509cdee8bbb9a7ea36ee1dc461377c68928d39c8b89e4669ff14
|
| 3 |
size 3849614
|
SnowballTarget/SnowballTarget-200112.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c03ee03e47e4fa5dab20cfe0849a6ff1877df60d2cdefa0b35559ea169ec0562
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-200112.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849614
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e42460bea34a577f7b3220fb2b286986dfb811d4f2d589965e21670421ae38c8
|
| 3 |
size 3849614
|
SnowballTarget/SnowballTarget-49936.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0514bbd7fe1f1077c95e0668a327230e5e392a998d308fd6f4a72ad39c4c3d09
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-49936.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64f2f12e8c630a3f067f7f462301849fd655e35eb7de8245ae29ba2e41b01c89
|
| 3 |
size 3849541
|
SnowballTarget/SnowballTarget-99960.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97fd2ccb667866e1edeb8b23458d9628438a01a3eb83fbe75e9c7413af8ad46a
|
| 3 |
size 650645
|
SnowballTarget/SnowballTarget-99960.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:152bd1eab9014b1be0f3cef086623b2a5de63c5912d74674a762cb6d53c1c4fc
|
| 3 |
size 3849541
|
SnowballTarget/checkpoint.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3848811
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdccf722a3ce5c9dc7972170389135c8dbbab25a993b04188ab02687809cb5bc
|
| 3 |
size 3848811
|
SnowballTarget/events.out.tfevents.1697022380.429c7995e803.804.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:129dfb2464eef2d03ec6e0a831d4fecd9bca1c9c4b519a30b3436bf626edbac4
|
| 3 |
+
size 28687
|
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": 0.0005, "epsilon": 0.1, "lambd": 0.9, "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": "
|
|
|
|
| 1 |
+
{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.0005, "epsilon": 0.1, "lambd": 0.9, "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": "SnowballTarget3", "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
|
@@ -65,7 +65,7 @@ engine_settings:
|
|
| 65 |
no_graphics: true
|
| 66 |
environment_parameters: null
|
| 67 |
checkpoint_settings:
|
| 68 |
-
run_id:
|
| 69 |
initialize_from: null
|
| 70 |
load_model: false
|
| 71 |
resume: false
|
|
|
|
| 65 |
no_graphics: true
|
| 66 |
environment_parameters: null
|
| 67 |
checkpoint_settings:
|
| 68 |
+
run_id: SnowballTarget3
|
| 69 |
initialize_from: null
|
| 70 |
load_model: false
|
| 71 |
resume: false
|
run_logs/Player-0.log
CHANGED
|
@@ -34,7 +34,7 @@ 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.
|
| 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 +45,7 @@ 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.
|
| 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 +53,7 @@ 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]:
|
| 57 |
Initial Block Size 4.0 MB
|
| 58 |
Current Block Size 4.0 MB
|
| 59 |
Peak Allocated Bytes 2.0 MB
|
|
@@ -169,23 +169,23 @@ Memory Statistics:
|
|
| 169 |
Peak Allocated Bytes 0 B
|
| 170 |
Overflow Count 0
|
| 171 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
| 172 |
-
Peak main deferred allocation count
|
| 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: [
|
| 179 |
Requested Block Size 16.0 MB
|
| 180 |
Peak Block count 1
|
| 181 |
-
Peak Allocated memory
|
| 182 |
-
Peak Large allocation bytes 0
|
| 183 |
[ALLOC_DEFAULT_THREAD]
|
| 184 |
-
Peak usage frame count: [
|
| 185 |
Requested Block Size 16.0 MB
|
| 186 |
Peak Block count 1
|
| 187 |
-
Peak Allocated memory
|
| 188 |
-
Peak Large allocation bytes
|
| 189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
| 190 |
Initial Block Size 2.0 MB
|
| 191 |
Used Block Count 1
|
|
@@ -213,13 +213,13 @@ 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]:
|
| 217 |
Requested Block Size 16.0 MB
|
| 218 |
Peak Block count 1
|
| 219 |
-
Peak Allocated memory 66.
|
| 220 |
Peak Large allocation bytes 0 B
|
| 221 |
[ALLOC_GFX_THREAD]
|
| 222 |
-
Peak usage frame count: [32.0 KB-64.0 KB]:
|
| 223 |
Requested Block Size 16.0 MB
|
| 224 |
Peak Block count 1
|
| 225 |
Peak Allocated memory 39.6 KB
|
|
@@ -231,13 +231,13 @@ 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]:
|
| 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]:
|
| 241 |
Requested Block Size 4.0 MB
|
| 242 |
Peak Block count 1
|
| 243 |
Peak Allocated memory 2.2 MB
|
|
@@ -249,13 +249,13 @@ 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]:
|
| 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]:
|
| 259 |
Requested Block Size 2.0 MB
|
| 260 |
Peak Block count 1
|
| 261 |
Peak Allocated memory 1.7 KB
|
|
|
|
| 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 0.123 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 |
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: 0.775956 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 |
[ALLOC_TEMP_TLS] TLS Allocator
|
| 54 |
StackAllocators :
|
| 55 |
[ALLOC_TEMP_MAIN]
|
| 56 |
+
Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
|
| 57 |
Initial Block Size 4.0 MB
|
| 58 |
Current Block Size 4.0 MB
|
| 59 |
Peak Allocated Bytes 2.0 MB
|
|
|
|
| 169 |
Peak Allocated Bytes 0 B
|
| 170 |
Overflow Count 0
|
| 171 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
| 172 |
+
Peak main deferred allocation count 38
|
| 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: [16.0 MB-32.0 MB]: 5461 frames
|
| 179 |
Requested Block Size 16.0 MB
|
| 180 |
Peak Block count 1
|
| 181 |
+
Peak Allocated memory 22.6 MB
|
| 182 |
+
Peak Large allocation bytes 16.0 MB
|
| 183 |
[ALLOC_DEFAULT_THREAD]
|
| 184 |
+
Peak usage frame count: [1.0 MB-2.0 MB]: 5461 frames
|
| 185 |
Requested Block Size 16.0 MB
|
| 186 |
Peak Block count 1
|
| 187 |
+
Peak Allocated memory 1.7 MB
|
| 188 |
+
Peak Large allocation bytes 0 B
|
| 189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
| 190 |
Initial Block Size 2.0 MB
|
| 191 |
Used Block Count 1
|
|
|
|
| 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]: 5050 frames, [64.0 KB-128.0 KB]: 411 frames
|
| 217 |
Requested Block Size 16.0 MB
|
| 218 |
Peak Block count 1
|
| 219 |
+
Peak Allocated memory 66.4 KB
|
| 220 |
Peak Large allocation bytes 0 B
|
| 221 |
[ALLOC_GFX_THREAD]
|
| 222 |
+
Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
|
| 223 |
Requested Block Size 16.0 MB
|
| 224 |
Peak Block count 1
|
| 225 |
Peak Allocated memory 39.6 KB
|
|
|
|
| 231 |
Used Block count 1
|
| 232 |
Peak Allocated bytes 1.0 MB
|
| 233 |
[ALLOC_CACHEOBJECTS_MAIN]
|
| 234 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 5461 frames
|
| 235 |
Requested Block Size 4.0 MB
|
| 236 |
Peak Block count 1
|
| 237 |
Peak Allocated memory 0.6 MB
|
| 238 |
Peak Large allocation bytes 0 B
|
| 239 |
[ALLOC_CACHEOBJECTS_THREAD]
|
| 240 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
|
| 241 |
Requested Block Size 4.0 MB
|
| 242 |
Peak Block count 1
|
| 243 |
Peak Allocated memory 2.2 MB
|
|
|
|
| 249 |
Used Block count 1
|
| 250 |
Peak Allocated bytes 1.0 MB
|
| 251 |
[ALLOC_TYPETREE_MAIN]
|
| 252 |
+
Peak usage frame count: [0-1.0 KB]: 5461 frames
|
| 253 |
Requested Block Size 2.0 MB
|
| 254 |
Peak Block count 1
|
| 255 |
Peak Allocated memory 1.0 KB
|
| 256 |
Peak Large allocation bytes 0 B
|
| 257 |
[ALLOC_TYPETREE_THREAD]
|
| 258 |
+
Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
|
| 259 |
Requested Block Size 2.0 MB
|
| 260 |
Peak Block count 1
|
| 261 |
Peak Allocated memory 1.7 KB
|
run_logs/timers.json
CHANGED
|
@@ -2,15 +2,15 @@
|
|
| 2 |
"name": "root",
|
| 3 |
"gauges": {
|
| 4 |
"SnowballTarget.Policy.Entropy.mean": {
|
| 5 |
-
"value": 1.
|
| 6 |
-
"min":
|
| 7 |
-
"max": 2.
|
| 8 |
"count": 20
|
| 9 |
},
|
| 10 |
"SnowballTarget.Policy.Entropy.sum": {
|
| 11 |
-
"value":
|
| 12 |
-
"min":
|
| 13 |
-
"max":
|
| 14 |
"count": 20
|
| 15 |
},
|
| 16 |
"SnowballTarget.Step.mean": {
|
|
@@ -26,15 +26,15 @@
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
-
"value": 12.
|
| 30 |
-
"min": 0.
|
| 31 |
-
"max": 12.
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
-
"value":
|
| 36 |
-
"min":
|
| 37 |
-
"max":
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
@@ -50,27 +50,27 @@
|
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 53 |
-
"value": 0.
|
| 54 |
-
"min": 0.
|
| 55 |
-
"max": 0.
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 59 |
-
"value": 0.
|
| 60 |
-
"min": 0.
|
| 61 |
-
"max": 0.
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 65 |
-
"value": 0.
|
| 66 |
-
"min": 0.
|
| 67 |
-
"max": 0.
|
| 68 |
"count": 20
|
| 69 |
},
|
| 70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 71 |
-
"value": 0.
|
| 72 |
-
"min": 0.
|
| 73 |
-
"max": 0.
|
| 74 |
"count": 20
|
| 75 |
},
|
| 76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
@@ -110,27 +110,27 @@
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
-
"value":
|
| 114 |
-
"min":
|
| 115 |
-
"max": 25.
|
| 116 |
"count": 20
|
| 117 |
},
|
| 118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
| 119 |
-
"value":
|
| 120 |
-
"min":
|
| 121 |
-
"max":
|
| 122 |
"count": 20
|
| 123 |
},
|
| 124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
| 125 |
-
"value":
|
| 126 |
-
"min":
|
| 127 |
-
"max": 25.
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
-
"value":
|
| 132 |
-
"min":
|
| 133 |
-
"max":
|
| 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": "
|
| 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=
|
| 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": "2.0.1+cu118",
|
| 158 |
-
"numpy_version": "1.
|
| 159 |
-
"end_time_seconds": "
|
| 160 |
},
|
| 161 |
-
"total":
|
| 162 |
"count": 1,
|
| 163 |
-
"self": 0.
|
| 164 |
"children": {
|
| 165 |
"run_training.setup": {
|
| 166 |
-
"total": 0.
|
| 167 |
"count": 1,
|
| 168 |
-
"self": 0.
|
| 169 |
},
|
| 170 |
"TrainerController.start_learning": {
|
| 171 |
-
"total":
|
| 172 |
"count": 1,
|
| 173 |
-
"self": 0.
|
| 174 |
"children": {
|
| 175 |
"TrainerController._reset_env": {
|
| 176 |
-
"total": 8.
|
| 177 |
"count": 1,
|
| 178 |
-
"self": 8.
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
-
"total":
|
| 182 |
-
"count":
|
| 183 |
-
"self": 0.
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
-
"total":
|
| 187 |
-
"count":
|
| 188 |
-
"self":
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
-
"total":
|
| 192 |
-
"count":
|
| 193 |
-
"self": 1.
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
-
"total":
|
| 197 |
-
"count":
|
| 198 |
-
"self":
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
-
"total": 0.
|
| 204 |
-
"count":
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
-
"total":
|
| 209 |
-
"count":
|
| 210 |
"is_parallel": true,
|
| 211 |
-
"self":
|
| 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.
|
| 221 |
"count": 1,
|
| 222 |
"is_parallel": true,
|
| 223 |
-
"self": 0.
|
| 224 |
"children": {
|
| 225 |
"_process_rank_one_or_two_observation": {
|
| 226 |
-
"total": 0.
|
| 227 |
"count": 10,
|
| 228 |
"is_parallel": true,
|
| 229 |
-
"self": 0.
|
| 230 |
}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
"UnityEnvironment.step": {
|
| 234 |
-
"total": 0.
|
| 235 |
"count": 1,
|
| 236 |
"is_parallel": true,
|
| 237 |
-
"self": 0.
|
| 238 |
"children": {
|
| 239 |
"UnityEnvironment._generate_step_input": {
|
| 240 |
-
"total": 0.
|
| 241 |
"count": 1,
|
| 242 |
"is_parallel": true,
|
| 243 |
-
"self": 0.
|
| 244 |
},
|
| 245 |
"communicator.exchange": {
|
| 246 |
-
"total": 0.
|
| 247 |
"count": 1,
|
| 248 |
"is_parallel": true,
|
| 249 |
-
"self": 0.
|
| 250 |
},
|
| 251 |
"steps_from_proto": {
|
| 252 |
-
"total": 0.
|
| 253 |
"count": 1,
|
| 254 |
"is_parallel": true,
|
| 255 |
-
"self": 0.
|
| 256 |
"children": {
|
| 257 |
"_process_rank_one_or_two_observation": {
|
| 258 |
-
"total": 0.
|
| 259 |
"count": 10,
|
| 260 |
"is_parallel": true,
|
| 261 |
-
"self": 0.
|
| 262 |
}
|
| 263 |
}
|
| 264 |
}
|
|
@@ -267,34 +267,34 @@
|
|
| 267 |
}
|
| 268 |
},
|
| 269 |
"UnityEnvironment.step": {
|
| 270 |
-
"total":
|
| 271 |
-
"count":
|
| 272 |
"is_parallel": true,
|
| 273 |
-
"self": 10.
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
-
"total": 5.
|
| 277 |
-
"count":
|
| 278 |
"is_parallel": true,
|
| 279 |
-
"self": 5.
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
-
"total": 187.
|
| 283 |
-
"count":
|
| 284 |
"is_parallel": true,
|
| 285 |
-
"self": 187.
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
-
"total":
|
| 289 |
-
"count":
|
| 290 |
"is_parallel": true,
|
| 291 |
-
"self": 6.
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
-
"total":
|
| 295 |
-
"count":
|
| 296 |
"is_parallel": true,
|
| 297 |
-
"self":
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
@@ -309,9 +309,9 @@
|
|
| 309 |
}
|
| 310 |
},
|
| 311 |
"trainer_threads": {
|
| 312 |
-
"total": 0.
|
| 313 |
"count": 1,
|
| 314 |
-
"self": 0.
|
| 315 |
"children": {
|
| 316 |
"thread_root": {
|
| 317 |
"total": 0.0,
|
|
@@ -320,36 +320,36 @@
|
|
| 320 |
"self": 0.0,
|
| 321 |
"children": {
|
| 322 |
"trainer_advance": {
|
| 323 |
-
"total":
|
| 324 |
-
"count":
|
| 325 |
"is_parallel": true,
|
| 326 |
-
"self": 9.
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
-
"total": 252.
|
| 330 |
-
"count":
|
| 331 |
"is_parallel": true,
|
| 332 |
-
"self": 251.
|
| 333 |
"children": {
|
| 334 |
"RLTrainer._checkpoint": {
|
| 335 |
-
"total":
|
| 336 |
"count": 4,
|
| 337 |
"is_parallel": true,
|
| 338 |
-
"self":
|
| 339 |
}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"_update_policy": {
|
| 343 |
-
"total":
|
| 344 |
"count": 90,
|
| 345 |
"is_parallel": true,
|
| 346 |
-
"self":
|
| 347 |
"children": {
|
| 348 |
"TorchPPOOptimizer.update": {
|
| 349 |
-
"total":
|
| 350 |
"count": 4584,
|
| 351 |
"is_parallel": true,
|
| 352 |
-
"self":
|
| 353 |
}
|
| 354 |
}
|
| 355 |
}
|
|
@@ -360,14 +360,14 @@
|
|
| 360 |
}
|
| 361 |
},
|
| 362 |
"TrainerController._save_models": {
|
| 363 |
-
"total": 0.
|
| 364 |
"count": 1,
|
| 365 |
-
"self": 0.
|
| 366 |
"children": {
|
| 367 |
"RLTrainer._checkpoint": {
|
| 368 |
-
"total": 0.
|
| 369 |
"count": 1,
|
| 370 |
-
"self": 0.
|
| 371 |
}
|
| 372 |
}
|
| 373 |
}
|
|
|
|
| 2 |
"name": "root",
|
| 3 |
"gauges": {
|
| 4 |
"SnowballTarget.Policy.Entropy.mean": {
|
| 5 |
+
"value": 1.0011041164398193,
|
| 6 |
+
"min": 0.9854599833488464,
|
| 7 |
+
"max": 2.8815367221832275,
|
| 8 |
"count": 20
|
| 9 |
},
|
| 10 |
"SnowballTarget.Policy.Entropy.sum": {
|
| 11 |
+
"value": 9569.5546875,
|
| 12 |
+
"min": 9569.5546875,
|
| 13 |
+
"max": 29509.818359375,
|
| 14 |
"count": 20
|
| 15 |
},
|
| 16 |
"SnowballTarget.Step.mean": {
|
|
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
+
"value": 12.578500747680664,
|
| 30 |
+
"min": 0.19108004868030548,
|
| 31 |
+
"max": 12.578500747680664,
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
+
"value": 2452.8076171875,
|
| 36 |
+
"min": 37.06953048706055,
|
| 37 |
+
"max": 2524.880859375,
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
|
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 53 |
+
"value": 0.07006441180762041,
|
| 54 |
+
"min": 0.06301057839386083,
|
| 55 |
+
"max": 0.07316058867373595,
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 59 |
+
"value": 0.28025764723048163,
|
| 60 |
+
"min": 0.2520423135754433,
|
| 61 |
+
"max": 0.36580294336867974,
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 65 |
+
"value": 0.12994428041080633,
|
| 66 |
+
"min": 0.057764980759398614,
|
| 67 |
+
"max": 0.18183373160221997,
|
| 68 |
"count": 20
|
| 69 |
},
|
| 70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 71 |
+
"value": 0.5197771216432253,
|
| 72 |
+
"min": 0.23105992303759446,
|
| 73 |
+
"max": 0.9091686580110998,
|
| 74 |
"count": 20
|
| 75 |
},
|
| 76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
+
"value": 25.181818181818183,
|
| 114 |
+
"min": 2.75,
|
| 115 |
+
"max": 25.59090909090909,
|
| 116 |
"count": 20
|
| 117 |
},
|
| 118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
| 119 |
+
"value": 1108.0,
|
| 120 |
+
"min": 121.0,
|
| 121 |
+
"max": 1380.0,
|
| 122 |
"count": 20
|
| 123 |
},
|
| 124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
| 125 |
+
"value": 25.181818181818183,
|
| 126 |
+
"min": 2.75,
|
| 127 |
+
"max": 25.59090909090909,
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
+
"value": 1108.0,
|
| 132 |
+
"min": 121.0,
|
| 133 |
+
"max": 1380.0,
|
| 134 |
"count": 20
|
| 135 |
},
|
| 136 |
"SnowballTarget.IsTraining.mean": {
|
|
|
|
| 148 |
},
|
| 149 |
"metadata": {
|
| 150 |
"timer_format_version": "0.1.0",
|
| 151 |
+
"start_time_seconds": "1697022379",
|
| 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=SnowballTarget3 --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": "2.0.1+cu118",
|
| 158 |
+
"numpy_version": "1.23.5",
|
| 159 |
+
"end_time_seconds": "1697022838"
|
| 160 |
},
|
| 161 |
+
"total": 459.29682413800003,
|
| 162 |
"count": 1,
|
| 163 |
+
"self": 0.42865565100009917,
|
| 164 |
"children": {
|
| 165 |
"run_training.setup": {
|
| 166 |
+
"total": 0.07023954599998206,
|
| 167 |
"count": 1,
|
| 168 |
+
"self": 0.07023954599998206
|
| 169 |
},
|
| 170 |
"TrainerController.start_learning": {
|
| 171 |
+
"total": 458.79792894099995,
|
| 172 |
"count": 1,
|
| 173 |
+
"self": 0.5331379969945829,
|
| 174 |
"children": {
|
| 175 |
"TrainerController._reset_env": {
|
| 176 |
+
"total": 8.022404402999996,
|
| 177 |
"count": 1,
|
| 178 |
+
"self": 8.022404402999996
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
+
"total": 450.1529573780053,
|
| 182 |
+
"count": 18201,
|
| 183 |
+
"self": 0.27231736501255455,
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
+
"total": 449.8806400129927,
|
| 187 |
+
"count": 18201,
|
| 188 |
+
"self": 308.3696353230033,
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
+
"total": 141.23643191399898,
|
| 192 |
+
"count": 18201,
|
| 193 |
+
"self": 1.3901599339927486,
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
+
"total": 139.84627198000624,
|
| 197 |
+
"count": 18201,
|
| 198 |
+
"self": 139.84627198000624
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
+
"total": 0.2745727759904355,
|
| 204 |
+
"count": 18201,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
+
"total": 457.5795183950001,
|
| 209 |
+
"count": 18201,
|
| 210 |
"is_parallel": true,
|
| 211 |
+
"self": 221.65946265499912,
|
| 212 |
"children": {
|
| 213 |
"run_training.setup": {
|
| 214 |
"total": 0.0,
|
|
|
|
| 217 |
"self": 0.0,
|
| 218 |
"children": {
|
| 219 |
"steps_from_proto": {
|
| 220 |
+
"total": 0.006454921999988983,
|
| 221 |
"count": 1,
|
| 222 |
"is_parallel": true,
|
| 223 |
+
"self": 0.0043369920000202455,
|
| 224 |
"children": {
|
| 225 |
"_process_rank_one_or_two_observation": {
|
| 226 |
+
"total": 0.0021179299999687373,
|
| 227 |
"count": 10,
|
| 228 |
"is_parallel": true,
|
| 229 |
+
"self": 0.0021179299999687373
|
| 230 |
}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
"UnityEnvironment.step": {
|
| 234 |
+
"total": 0.046302088999993884,
|
| 235 |
"count": 1,
|
| 236 |
"is_parallel": true,
|
| 237 |
+
"self": 0.0007049269999868102,
|
| 238 |
"children": {
|
| 239 |
"UnityEnvironment._generate_step_input": {
|
| 240 |
+
"total": 0.00041053000001056716,
|
| 241 |
"count": 1,
|
| 242 |
"is_parallel": true,
|
| 243 |
+
"self": 0.00041053000001056716
|
| 244 |
},
|
| 245 |
"communicator.exchange": {
|
| 246 |
+
"total": 0.0430446409999945,
|
| 247 |
"count": 1,
|
| 248 |
"is_parallel": true,
|
| 249 |
+
"self": 0.0430446409999945
|
| 250 |
},
|
| 251 |
"steps_from_proto": {
|
| 252 |
+
"total": 0.002141991000002008,
|
| 253 |
"count": 1,
|
| 254 |
"is_parallel": true,
|
| 255 |
+
"self": 0.0005320419999748083,
|
| 256 |
"children": {
|
| 257 |
"_process_rank_one_or_two_observation": {
|
| 258 |
+
"total": 0.0016099490000271999,
|
| 259 |
"count": 10,
|
| 260 |
"is_parallel": true,
|
| 261 |
+
"self": 0.0016099490000271999
|
| 262 |
}
|
| 263 |
}
|
| 264 |
}
|
|
|
|
| 267 |
}
|
| 268 |
},
|
| 269 |
"UnityEnvironment.step": {
|
| 270 |
+
"total": 235.92005574000098,
|
| 271 |
+
"count": 18200,
|
| 272 |
"is_parallel": true,
|
| 273 |
+
"self": 10.346040903989376,
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
+
"total": 5.280943166008768,
|
| 277 |
+
"count": 18200,
|
| 278 |
"is_parallel": true,
|
| 279 |
+
"self": 5.280943166008768
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
+
"total": 187.50584912600237,
|
| 283 |
+
"count": 18200,
|
| 284 |
"is_parallel": true,
|
| 285 |
+
"self": 187.50584912600237
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
+
"total": 32.78722254400046,
|
| 289 |
+
"count": 18200,
|
| 290 |
"is_parallel": true,
|
| 291 |
+
"self": 6.083201813000926,
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
+
"total": 26.70402073099953,
|
| 295 |
+
"count": 182000,
|
| 296 |
"is_parallel": true,
|
| 297 |
+
"self": 26.70402073099953
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
|
|
| 309 |
}
|
| 310 |
},
|
| 311 |
"trainer_threads": {
|
| 312 |
+
"total": 0.00011632400003236398,
|
| 313 |
"count": 1,
|
| 314 |
+
"self": 0.00011632400003236398,
|
| 315 |
"children": {
|
| 316 |
"thread_root": {
|
| 317 |
"total": 0.0,
|
|
|
|
| 320 |
"self": 0.0,
|
| 321 |
"children": {
|
| 322 |
"trainer_advance": {
|
| 323 |
+
"total": 446.50971218698254,
|
| 324 |
+
"count": 461109,
|
| 325 |
"is_parallel": true,
|
| 326 |
+
"self": 9.826753579985109,
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
+
"total": 252.41192288799775,
|
| 330 |
+
"count": 461109,
|
| 331 |
"is_parallel": true,
|
| 332 |
+
"self": 251.5467383439977,
|
| 333 |
"children": {
|
| 334 |
"RLTrainer._checkpoint": {
|
| 335 |
+
"total": 0.8651845440000443,
|
| 336 |
"count": 4,
|
| 337 |
"is_parallel": true,
|
| 338 |
+
"self": 0.8651845440000443
|
| 339 |
}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"_update_policy": {
|
| 343 |
+
"total": 184.27103571899968,
|
| 344 |
"count": 90,
|
| 345 |
"is_parallel": true,
|
| 346 |
+
"self": 57.27244771899555,
|
| 347 |
"children": {
|
| 348 |
"TorchPPOOptimizer.update": {
|
| 349 |
+
"total": 126.99858800000413,
|
| 350 |
"count": 4584,
|
| 351 |
"is_parallel": true,
|
| 352 |
+
"self": 126.99858800000413
|
| 353 |
}
|
| 354 |
}
|
| 355 |
}
|
|
|
|
| 360 |
}
|
| 361 |
},
|
| 362 |
"TrainerController._save_models": {
|
| 363 |
+
"total": 0.08931283900005837,
|
| 364 |
"count": 1,
|
| 365 |
+
"self": 0.0011601680000694614,
|
| 366 |
"children": {
|
| 367 |
"RLTrainer._checkpoint": {
|
| 368 |
+
"total": 0.08815267099998891,
|
| 369 |
"count": 1,
|
| 370 |
+
"self": 0.08815267099998891
|
| 371 |
}
|
| 372 |
}
|
| 373 |
}
|
run_logs/training_status.json
CHANGED
|
@@ -3,57 +3,57 @@
|
|
| 3 |
"checkpoints": [
|
| 4 |
{
|
| 5 |
"steps": 49936,
|
| 6 |
-
"file_path": "results/
|
| 7 |
-
"reward":
|
| 8 |
-
"creation_time":
|
| 9 |
"auxillary_file_paths": [
|
| 10 |
-
"results/
|
| 11 |
]
|
| 12 |
},
|
| 13 |
{
|
| 14 |
"steps": 99960,
|
| 15 |
-
"file_path": "results/
|
| 16 |
-
"reward":
|
| 17 |
-
"creation_time":
|
| 18 |
"auxillary_file_paths": [
|
| 19 |
-
"results/
|
| 20 |
]
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"steps": 149984,
|
| 24 |
-
"file_path": "results/
|
| 25 |
-
"reward":
|
| 26 |
-
"creation_time":
|
| 27 |
"auxillary_file_paths": [
|
| 28 |
-
"results/
|
| 29 |
]
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"steps": 199984,
|
| 33 |
-
"file_path": "results/
|
| 34 |
-
"reward": 25.
|
| 35 |
-
"creation_time":
|
| 36 |
"auxillary_file_paths": [
|
| 37 |
-
"results/
|
| 38 |
]
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"steps": 200112,
|
| 42 |
-
"file_path": "results/
|
| 43 |
-
"reward": 25.
|
| 44 |
-
"creation_time":
|
| 45 |
"auxillary_file_paths": [
|
| 46 |
-
"results/
|
| 47 |
]
|
| 48 |
}
|
| 49 |
],
|
| 50 |
"final_checkpoint": {
|
| 51 |
"steps": 200112,
|
| 52 |
-
"file_path": "results/
|
| 53 |
-
"reward": 25.
|
| 54 |
-
"creation_time":
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
-
"results/
|
| 57 |
]
|
| 58 |
}
|
| 59 |
},
|
|
|
|
| 3 |
"checkpoints": [
|
| 4 |
{
|
| 5 |
"steps": 49936,
|
| 6 |
+
"file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.onnx",
|
| 7 |
+
"reward": 12.454545454545455,
|
| 8 |
+
"creation_time": 1697022503.1849778,
|
| 9 |
"auxillary_file_paths": [
|
| 10 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-49936.pt"
|
| 11 |
]
|
| 12 |
},
|
| 13 |
{
|
| 14 |
"steps": 99960,
|
| 15 |
+
"file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.onnx",
|
| 16 |
+
"reward": 20.727272727272727,
|
| 17 |
+
"creation_time": 1697022616.9330583,
|
| 18 |
"auxillary_file_paths": [
|
| 19 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-99960.pt"
|
| 20 |
]
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"steps": 149984,
|
| 24 |
+
"file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.onnx",
|
| 25 |
+
"reward": 23.272727272727273,
|
| 26 |
+
"creation_time": 1697022728.0160973,
|
| 27 |
"auxillary_file_paths": [
|
| 28 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-149984.pt"
|
| 29 |
]
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"steps": 199984,
|
| 33 |
+
"file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.onnx",
|
| 34 |
+
"reward": 25.818181818181817,
|
| 35 |
+
"creation_time": 1697022838.1728454,
|
| 36 |
"auxillary_file_paths": [
|
| 37 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-199984.pt"
|
| 38 |
]
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"steps": 200112,
|
| 42 |
+
"file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.onnx",
|
| 43 |
+
"reward": 25.818181818181817,
|
| 44 |
+
"creation_time": 1697022838.2834058,
|
| 45 |
"auxillary_file_paths": [
|
| 46 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
|
| 47 |
]
|
| 48 |
}
|
| 49 |
],
|
| 50 |
"final_checkpoint": {
|
| 51 |
"steps": 200112,
|
| 52 |
+
"file_path": "results/SnowballTarget3/SnowballTarget.onnx",
|
| 53 |
+
"reward": 25.818181818181817,
|
| 54 |
+
"creation_time": 1697022838.2834058,
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
+
"results/SnowballTarget3/SnowballTarget/SnowballTarget-200112.pt"
|
| 57 |
]
|
| 58 |
}
|
| 59 |
},
|