Reinforcement Learning
ml-agents
TensorBoard
ONNX
SnowballTarget
deep-reinforcement-learning
ML-Agents-SnowballTarget
Instructions to use MasumSIAT/ppo-SnowballTarget with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use MasumSIAT/ppo-SnowballTarget with ml-agents:
mlagents-load-from-hf --repo-id="MasumSIAT/ppo-SnowballTarget" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
First 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.1748331593.37d95edb02d9.4846.0 +3 -0
- run_logs/Player-0.log +6 -6
- run_logs/timers.json +97 -97
- run_logs/training_status.json +12 -12
SnowballTarget.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:030aa85c09f641a303a92006763e8c8b59197ef0d3abd78b466168f9ec5b8c36
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-149984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:281bbd39cfddce0b002068597a6df47bcaed2d3247a31087ecdfe4e86e7b212a
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-149984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91666cfcec61053528204e402e5adee0e747cc2d337515193638fd384fc805e2
|
| 3 |
size 3850564
|
SnowballTarget/SnowballTarget-199984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:030aa85c09f641a303a92006763e8c8b59197ef0d3abd78b466168f9ec5b8c36
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-199984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7caa4ad7a94212d8b62971af7b2079b3c968ba20d2c48c07ab8a74c9594241ad
|
| 3 |
size 3850564
|
SnowballTarget/SnowballTarget-200112.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:030aa85c09f641a303a92006763e8c8b59197ef0d3abd78b466168f9ec5b8c36
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-200112.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01d2c56c22967a29733be8742f314425c050cb28d0076adfec473d7358a31530
|
| 3 |
size 3850564
|
SnowballTarget/SnowballTarget-49936.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc32ae5d220facf26f576fc2149b434ee85e7e2dd7162cc4411397437423909d
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-49936.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850487
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bdeb6499f4f98ab0c3b90d2b5317efa83722bf4dbe157b4e003520384c9645a
|
| 3 |
size 3850487
|
SnowballTarget/SnowballTarget-99960.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650646
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cec511dcecfa91b3b6fca430904f322fc91d87c52937ce166b7e78694bc95ab
|
| 3 |
size 650646
|
SnowballTarget/SnowballTarget-99960.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850487
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ae7d5fe4256348170e6cf28f3111744c0a0d5c5c44d1213868c5f7fc275912a
|
| 3 |
size 3850487
|
SnowballTarget/checkpoint.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3849717
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:470fe1a38b3037523bb2738d0921ce494a4daa220853ca6537f7fef08b93a7d5
|
| 3 |
size 3849717
|
SnowballTarget/events.out.tfevents.1748331593.37d95edb02d9.4846.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d840c9623ffb3fbeea665f47efdea961d051711ad11e9221cfe971f604480e65
|
| 3 |
+
size 23427
|
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.
|
|
@@ -169,7 +169,7 @@ 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
|
|
@@ -178,13 +178,13 @@ Memory Statistics:
|
|
| 178 |
Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
|
| 179 |
Requested Block Size 16.0 MB
|
| 180 |
Peak Block count 1
|
| 181 |
-
Peak Allocated memory 6.
|
| 182 |
Peak Large allocation bytes 0 B
|
| 183 |
[ALLOC_DEFAULT_THREAD]
|
| 184 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
|
| 185 |
Requested Block Size 16.0 MB
|
| 186 |
Peak Block count 1
|
| 187 |
-
Peak Allocated memory 17.
|
| 188 |
Peak Large allocation bytes 16.0 MB
|
| 189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
| 190 |
Initial Block Size 2.0 MB
|
|
@@ -213,7 +213,7 @@ 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 67.3 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 0.088 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: 0.690895 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.
|
|
|
|
| 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
|
|
|
|
| 178 |
Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
|
| 179 |
Requested Block Size 16.0 MB
|
| 180 |
Peak Block count 1
|
| 181 |
+
Peak Allocated memory 6.5 MB
|
| 182 |
Peak Large allocation bytes 0 B
|
| 183 |
[ALLOC_DEFAULT_THREAD]
|
| 184 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
|
| 185 |
Requested Block Size 16.0 MB
|
| 186 |
Peak Block count 1
|
| 187 |
+
Peak Allocated memory 17.8 MB
|
| 188 |
Peak Large allocation bytes 16.0 MB
|
| 189 |
[ALLOC_TEMP_JOB_1_FRAME]
|
| 190 |
Initial Block Size 2.0 MB
|
|
|
|
| 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]: 4351 frames, [64.0 KB-128.0 KB]: 1107 frames
|
| 217 |
Requested Block Size 16.0 MB
|
| 218 |
Peak Block count 1
|
| 219 |
Peak Allocated memory 67.3 KB
|
run_logs/timers.json
CHANGED
|
@@ -2,15 +2,15 @@
|
|
| 2 |
"name": "root",
|
| 3 |
"gauges": {
|
| 4 |
"SnowballTarget.Policy.Entropy.mean": {
|
| 5 |
-
"value": 0.
|
| 6 |
-
"min": 0.
|
| 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": {
|
|
@@ -26,39 +26,39 @@
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
-
"value":
|
| 30 |
-
"min": 0.
|
| 31 |
-
"max":
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
-
"value":
|
| 36 |
-
"min":
|
| 37 |
-
"max":
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 41 |
-
"value": 0.
|
| 42 |
-
"min": 0.
|
| 43 |
-
"max": 0.
|
| 44 |
"count": 20
|
| 45 |
},
|
| 46 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 47 |
-
"value": 0.
|
| 48 |
-
"min": 0.
|
| 49 |
-
"max": 0.
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 53 |
-
"value": 0.
|
| 54 |
-
"min": 0.
|
| 55 |
-
"max": 0.
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 59 |
-
"value": 0.
|
| 60 |
-
"min": 0.
|
| 61 |
-
"max": 1.
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
@@ -110,27 +110,27 @@
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
-
"value":
|
| 114 |
-
"min": 3.
|
| 115 |
-
"max":
|
| 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": 3.
|
| 127 |
-
"max":
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
-
"value":
|
| 132 |
-
"min":
|
| 133 |
-
"max":
|
| 134 |
"count": 20
|
| 135 |
},
|
| 136 |
"SnowballTarget.IsTraining.mean": {
|
|
@@ -148,7 +148,7 @@
|
|
| 148 |
},
|
| 149 |
"metadata": {
|
| 150 |
"timer_format_version": "0.1.0",
|
| 151 |
-
"start_time_seconds": "
|
| 152 |
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
|
| 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": "1.2.0.dev0",
|
|
@@ -156,59 +156,59 @@
|
|
| 156 |
"communication_protocol_version": "1.5.0",
|
| 157 |
"pytorch_version": "2.7.0+cu126",
|
| 158 |
"numpy_version": "1.23.5",
|
| 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": 3.
|
| 177 |
"count": 1,
|
| 178 |
-
"self": 3.
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
-
"total":
|
| 182 |
"count": 18192,
|
| 183 |
-
"self": 0.
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
-
"total":
|
| 187 |
"count": 18192,
|
| 188 |
-
"self":
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
-
"total":
|
| 192 |
"count": 18192,
|
| 193 |
-
"self": 1.
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
-
"total":
|
| 197 |
"count": 18192,
|
| 198 |
-
"self":
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
-
"total": 0.
|
| 204 |
"count": 18192,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
-
"total":
|
| 209 |
"count": 18192,
|
| 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": 18191,
|
| 272 |
"is_parallel": true,
|
| 273 |
-
"self": 10.
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
-
"total": 5.
|
| 277 |
"count": 18191,
|
| 278 |
"is_parallel": true,
|
| 279 |
-
"self": 5.
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
-
"total": 160.
|
| 283 |
"count": 18191,
|
| 284 |
"is_parallel": true,
|
| 285 |
-
"self": 160.
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
-
"total":
|
| 289 |
"count": 18191,
|
| 290 |
"is_parallel": true,
|
| 291 |
-
"self": 5.
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
-
"total": 26.
|
| 295 |
"count": 181910,
|
| 296 |
"is_parallel": true,
|
| 297 |
-
"self": 26.
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
@@ -307,31 +307,31 @@
|
|
| 307 |
}
|
| 308 |
},
|
| 309 |
"trainer_advance": {
|
| 310 |
-
"total":
|
| 311 |
"count": 18192,
|
| 312 |
-
"self": 0.
|
| 313 |
"children": {
|
| 314 |
"process_trajectory": {
|
| 315 |
-
"total": 27.
|
| 316 |
"count": 18192,
|
| 317 |
-
"self": 27.
|
| 318 |
"children": {
|
| 319 |
"RLTrainer._checkpoint": {
|
| 320 |
-
"total": 0.
|
| 321 |
"count": 4,
|
| 322 |
-
"self": 0.
|
| 323 |
}
|
| 324 |
}
|
| 325 |
},
|
| 326 |
"_update_policy": {
|
| 327 |
-
"total":
|
| 328 |
"count": 90,
|
| 329 |
-
"self":
|
| 330 |
"children": {
|
| 331 |
"TorchPPOOptimizer.update": {
|
| 332 |
-
"total":
|
| 333 |
"count": 4587,
|
| 334 |
-
"self":
|
| 335 |
}
|
| 336 |
}
|
| 337 |
}
|
|
@@ -340,19 +340,19 @@
|
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"trainer_threads": {
|
| 343 |
-
"total":
|
| 344 |
"count": 1,
|
| 345 |
-
"self":
|
| 346 |
},
|
| 347 |
"TrainerController._save_models": {
|
| 348 |
-
"total": 0.
|
| 349 |
"count": 1,
|
| 350 |
-
"self": 0.
|
| 351 |
"children": {
|
| 352 |
"RLTrainer._checkpoint": {
|
| 353 |
-
"total": 0.
|
| 354 |
"count": 1,
|
| 355 |
-
"self": 0.
|
| 356 |
}
|
| 357 |
}
|
| 358 |
}
|
|
|
|
| 2 |
"name": "root",
|
| 3 |
"gauges": {
|
| 4 |
"SnowballTarget.Policy.Entropy.mean": {
|
| 5 |
+
"value": 0.8970576524734497,
|
| 6 |
+
"min": 0.8970576524734497,
|
| 7 |
+
"max": 2.8403637409210205,
|
| 8 |
"count": 20
|
| 9 |
},
|
| 10 |
"SnowballTarget.Policy.Entropy.sum": {
|
| 11 |
+
"value": 8525.6357421875,
|
| 12 |
+
"min": 8525.6357421875,
|
| 13 |
+
"max": 28994.43359375,
|
| 14 |
"count": 20
|
| 15 |
},
|
| 16 |
"SnowballTarget.Step.mean": {
|
|
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
+
"value": 12.874951362609863,
|
| 30 |
+
"min": 0.32905933260917664,
|
| 31 |
+
"max": 12.874951362609863,
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
+
"value": 2510.615478515625,
|
| 36 |
+
"min": 63.83750915527344,
|
| 37 |
+
"max": 2614.80859375,
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 41 |
+
"value": 0.07368160740060928,
|
| 42 |
+
"min": 0.06242030373918277,
|
| 43 |
+
"max": 0.07368160740060928,
|
| 44 |
"count": 20
|
| 45 |
},
|
| 46 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 47 |
+
"value": 0.2947264296024371,
|
| 48 |
+
"min": 0.2551987001400751,
|
| 49 |
+
"max": 0.3558566852788869,
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 53 |
+
"value": 0.1872357389360082,
|
| 54 |
+
"min": 0.12415158011786201,
|
| 55 |
+
"max": 0.28948435574477793,
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 59 |
+
"value": 0.7489429557440328,
|
| 60 |
+
"min": 0.49660632047144804,
|
| 61 |
+
"max": 1.302871477954528,
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
+
"value": 25.613636363636363,
|
| 114 |
+
"min": 3.340909090909091,
|
| 115 |
+
"max": 25.613636363636363,
|
| 116 |
"count": 20
|
| 117 |
},
|
| 118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
| 119 |
+
"value": 1127.0,
|
| 120 |
+
"min": 147.0,
|
| 121 |
+
"max": 1380.0,
|
| 122 |
"count": 20
|
| 123 |
},
|
| 124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
| 125 |
+
"value": 25.613636363636363,
|
| 126 |
+
"min": 3.340909090909091,
|
| 127 |
+
"max": 25.613636363636363,
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
+
"value": 1127.0,
|
| 132 |
+
"min": 147.0,
|
| 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": "1748331592",
|
| 152 |
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
|
| 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": "1.2.0.dev0",
|
|
|
|
| 156 |
"communication_protocol_version": "1.5.0",
|
| 157 |
"pytorch_version": "2.7.0+cu126",
|
| 158 |
"numpy_version": "1.23.5",
|
| 159 |
+
"end_time_seconds": "1748332034"
|
| 160 |
},
|
| 161 |
+
"total": 441.652005011,
|
| 162 |
"count": 1,
|
| 163 |
+
"self": 0.4364390870000534,
|
| 164 |
"children": {
|
| 165 |
"run_training.setup": {
|
| 166 |
+
"total": 0.025183483000091655,
|
| 167 |
"count": 1,
|
| 168 |
+
"self": 0.025183483000091655
|
| 169 |
},
|
| 170 |
"TrainerController.start_learning": {
|
| 171 |
+
"total": 441.1903824409999,
|
| 172 |
"count": 1,
|
| 173 |
+
"self": 0.3921388489980018,
|
| 174 |
"children": {
|
| 175 |
"TrainerController._reset_env": {
|
| 176 |
+
"total": 3.222531694000054,
|
| 177 |
"count": 1,
|
| 178 |
+
"self": 3.222531694000054
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
+
"total": 437.47536167800195,
|
| 182 |
"count": 18192,
|
| 183 |
+
"self": 0.4230710830101998,
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
+
"total": 313.53873969399,
|
| 187 |
"count": 18192,
|
| 188 |
+
"self": 238.86728349900318,
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
+
"total": 74.44605896998269,
|
| 192 |
"count": 18192,
|
| 193 |
+
"self": 1.3505168339715965,
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
+
"total": 73.09554213601109,
|
| 197 |
"count": 18192,
|
| 198 |
+
"self": 73.09554213601109
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
+
"total": 0.22539722500414427,
|
| 204 |
"count": 18192,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
+
"total": 439.7514746370209,
|
| 209 |
"count": 18192,
|
| 210 |
"is_parallel": true,
|
| 211 |
+
"self": 230.59205889901955,
|
| 212 |
"children": {
|
| 213 |
"run_training.setup": {
|
| 214 |
"total": 0.0,
|
|
|
|
| 217 |
"self": 0.0,
|
| 218 |
"children": {
|
| 219 |
"steps_from_proto": {
|
| 220 |
+
"total": 0.006282369000018662,
|
| 221 |
"count": 1,
|
| 222 |
"is_parallel": true,
|
| 223 |
+
"self": 0.004211671000120987,
|
| 224 |
"children": {
|
| 225 |
"_process_rank_one_or_two_observation": {
|
| 226 |
+
"total": 0.002070697999897675,
|
| 227 |
"count": 10,
|
| 228 |
"is_parallel": true,
|
| 229 |
+
"self": 0.002070697999897675
|
| 230 |
}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
"UnityEnvironment.step": {
|
| 234 |
+
"total": 0.04017515900000035,
|
| 235 |
"count": 1,
|
| 236 |
"is_parallel": true,
|
| 237 |
+
"self": 0.0005976799998279603,
|
| 238 |
"children": {
|
| 239 |
"UnityEnvironment._generate_step_input": {
|
| 240 |
+
"total": 0.0004189030000816274,
|
| 241 |
"count": 1,
|
| 242 |
"is_parallel": true,
|
| 243 |
+
"self": 0.0004189030000816274
|
| 244 |
},
|
| 245 |
"communicator.exchange": {
|
| 246 |
+
"total": 0.0371630180000011,
|
| 247 |
"count": 1,
|
| 248 |
"is_parallel": true,
|
| 249 |
+
"self": 0.0371630180000011
|
| 250 |
},
|
| 251 |
"steps_from_proto": {
|
| 252 |
+
"total": 0.001995558000089659,
|
| 253 |
"count": 1,
|
| 254 |
"is_parallel": true,
|
| 255 |
+
"self": 0.0003712539994467079,
|
| 256 |
"children": {
|
| 257 |
"_process_rank_one_or_two_observation": {
|
| 258 |
+
"total": 0.001624304000642951,
|
| 259 |
"count": 10,
|
| 260 |
"is_parallel": true,
|
| 261 |
+
"self": 0.001624304000642951
|
| 262 |
}
|
| 263 |
}
|
| 264 |
}
|
|
|
|
| 267 |
}
|
| 268 |
},
|
| 269 |
"UnityEnvironment.step": {
|
| 270 |
+
"total": 209.15941573800137,
|
| 271 |
"count": 18191,
|
| 272 |
"is_parallel": true,
|
| 273 |
+
"self": 10.004286083030138,
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
+
"total": 5.5207426469933125,
|
| 277 |
"count": 18191,
|
| 278 |
"is_parallel": true,
|
| 279 |
+
"self": 5.5207426469933125
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
+
"total": 160.88923445700402,
|
| 283 |
"count": 18191,
|
| 284 |
"is_parallel": true,
|
| 285 |
+
"self": 160.88923445700402
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
+
"total": 32.7451525509739,
|
| 289 |
"count": 18191,
|
| 290 |
"is_parallel": true,
|
| 291 |
+
"self": 5.998116067978572,
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
+
"total": 26.747036482995327,
|
| 295 |
"count": 181910,
|
| 296 |
"is_parallel": true,
|
| 297 |
+
"self": 26.747036482995327
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
|
|
| 307 |
}
|
| 308 |
},
|
| 309 |
"trainer_advance": {
|
| 310 |
+
"total": 123.51355090100174,
|
| 311 |
"count": 18192,
|
| 312 |
+
"self": 0.49210280199326917,
|
| 313 |
"children": {
|
| 314 |
"process_trajectory": {
|
| 315 |
+
"total": 27.856054442007917,
|
| 316 |
"count": 18192,
|
| 317 |
+
"self": 27.444632671007867,
|
| 318 |
"children": {
|
| 319 |
"RLTrainer._checkpoint": {
|
| 320 |
+
"total": 0.4114217710000503,
|
| 321 |
"count": 4,
|
| 322 |
+
"self": 0.4114217710000503
|
| 323 |
}
|
| 324 |
}
|
| 325 |
},
|
| 326 |
"_update_policy": {
|
| 327 |
+
"total": 95.16539365700055,
|
| 328 |
"count": 90,
|
| 329 |
+
"self": 38.63965810699801,
|
| 330 |
"children": {
|
| 331 |
"TorchPPOOptimizer.update": {
|
| 332 |
+
"total": 56.52573555000254,
|
| 333 |
"count": 4587,
|
| 334 |
+
"self": 56.52573555000254
|
| 335 |
}
|
| 336 |
}
|
| 337 |
}
|
|
|
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"trainer_threads": {
|
| 343 |
+
"total": 8.249999154941179e-07,
|
| 344 |
"count": 1,
|
| 345 |
+
"self": 8.249999154941179e-07
|
| 346 |
},
|
| 347 |
"TrainerController._save_models": {
|
| 348 |
+
"total": 0.10034939499996653,
|
| 349 |
"count": 1,
|
| 350 |
+
"self": 0.0008359319999726722,
|
| 351 |
"children": {
|
| 352 |
"RLTrainer._checkpoint": {
|
| 353 |
+
"total": 0.09951346299999386,
|
| 354 |
"count": 1,
|
| 355 |
+
"self": 0.09951346299999386
|
| 356 |
}
|
| 357 |
}
|
| 358 |
}
|
run_logs/training_status.json
CHANGED
|
@@ -4,8 +4,8 @@
|
|
| 4 |
{
|
| 5 |
"steps": 49936,
|
| 6 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
|
| 7 |
-
"reward": 15.
|
| 8 |
-
"creation_time":
|
| 9 |
"auxillary_file_paths": [
|
| 10 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
|
| 11 |
]
|
|
@@ -13,8 +13,8 @@
|
|
| 13 |
{
|
| 14 |
"steps": 99960,
|
| 15 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
|
| 16 |
-
"reward": 21.
|
| 17 |
-
"creation_time":
|
| 18 |
"auxillary_file_paths": [
|
| 19 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
|
| 20 |
]
|
|
@@ -22,8 +22,8 @@
|
|
| 22 |
{
|
| 23 |
"steps": 149984,
|
| 24 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
|
| 25 |
-
"reward":
|
| 26 |
-
"creation_time":
|
| 27 |
"auxillary_file_paths": [
|
| 28 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
|
| 29 |
]
|
|
@@ -31,8 +31,8 @@
|
|
| 31 |
{
|
| 32 |
"steps": 199984,
|
| 33 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
|
| 34 |
-
"reward":
|
| 35 |
-
"creation_time":
|
| 36 |
"auxillary_file_paths": [
|
| 37 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
|
| 38 |
]
|
|
@@ -40,8 +40,8 @@
|
|
| 40 |
{
|
| 41 |
"steps": 200112,
|
| 42 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
|
| 43 |
-
"reward":
|
| 44 |
-
"creation_time":
|
| 45 |
"auxillary_file_paths": [
|
| 46 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
| 47 |
]
|
|
@@ -50,8 +50,8 @@
|
|
| 50 |
"final_checkpoint": {
|
| 51 |
"steps": 200112,
|
| 52 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
| 53 |
-
"reward":
|
| 54 |
-
"creation_time":
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
| 57 |
]
|
|
|
|
| 4 |
{
|
| 5 |
"steps": 49936,
|
| 6 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
|
| 7 |
+
"reward": 15.909090909090908,
|
| 8 |
+
"creation_time": 1748331705.6069646,
|
| 9 |
"auxillary_file_paths": [
|
| 10 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
|
| 11 |
]
|
|
|
|
| 13 |
{
|
| 14 |
"steps": 99960,
|
| 15 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
|
| 16 |
+
"reward": 21.363636363636363,
|
| 17 |
+
"creation_time": 1748331814.0562458,
|
| 18 |
"auxillary_file_paths": [
|
| 19 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
|
| 20 |
]
|
|
|
|
| 22 |
{
|
| 23 |
"steps": 149984,
|
| 24 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
|
| 25 |
+
"reward": 24.454545454545453,
|
| 26 |
+
"creation_time": 1748331924.8942516,
|
| 27 |
"auxillary_file_paths": [
|
| 28 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
|
| 29 |
]
|
|
|
|
| 31 |
{
|
| 32 |
"steps": 199984,
|
| 33 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
|
| 34 |
+
"reward": 25.727272727272727,
|
| 35 |
+
"creation_time": 1748332034.0593767,
|
| 36 |
"auxillary_file_paths": [
|
| 37 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
|
| 38 |
]
|
|
|
|
| 40 |
{
|
| 41 |
"steps": 200112,
|
| 42 |
"file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
|
| 43 |
+
"reward": 25.727272727272727,
|
| 44 |
+
"creation_time": 1748332034.1723194,
|
| 45 |
"auxillary_file_paths": [
|
| 46 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
| 47 |
]
|
|
|
|
| 50 |
"final_checkpoint": {
|
| 51 |
"steps": 200112,
|
| 52 |
"file_path": "results/SnowballTarget1/SnowballTarget.onnx",
|
| 53 |
+
"reward": 25.727272727272727,
|
| 54 |
+
"creation_time": 1748332034.1723194,
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
| 57 |
]
|