Commit
•
2dc8c6f
1
Parent(s):
462156f
First Push
Browse files- README.md +14 -8
- 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.1686488744.323e160b8448.1531.0 +3 -0
- run_logs/Player-0.log +6 -6
- run_logs/timers.json +100 -100
- run_logs/training_status.json +12 -12
README.md
CHANGED
|
@@ -8,21 +8,27 @@ tags:
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# **ppo** Agent playing **SnowballTarget**
|
| 11 |
-
This is a trained model of a **ppo** agent playing **SnowballTarget**
|
| 12 |
-
|
|
|
|
| 13 |
## Usage (with ML-Agents)
|
| 14 |
-
The Documentation: https://github.
|
| 15 |
-
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
### Resume the training
|
| 19 |
-
```
|
| 20 |
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
| 21 |
```
|
|
|
|
| 22 |
### Watch your Agent play
|
| 23 |
-
You can watch your agent **playing directly in your browser
|
| 24 |
-
|
| 25 |
-
1.
|
| 26 |
2. Step 1: Find your model_id: serkanBurakOrs/ppo-SnowballTarget
|
| 27 |
3. Step 2: Select your *.nn /*.onnx file
|
| 28 |
4. Click on Watch the agent play 👀
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# **ppo** Agent playing **SnowballTarget**
|
| 11 |
+
This is a trained model of a **ppo** agent playing **SnowballTarget**
|
| 12 |
+
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
| 13 |
+
|
| 14 |
## Usage (with ML-Agents)
|
| 15 |
+
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
|
|
|
|
| 16 |
|
| 17 |
+
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
| 18 |
+
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
|
| 19 |
+
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
|
| 20 |
+
- A *longer tutorial* to understand how works ML-Agents:
|
| 21 |
+
https://huggingface.co/learn/deep-rl-course/unit5/introduction
|
| 22 |
|
| 23 |
### Resume the training
|
| 24 |
+
```bash
|
| 25 |
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
| 26 |
```
|
| 27 |
+
|
| 28 |
### Watch your Agent play
|
| 29 |
+
You can watch your agent **playing directly in your browser**
|
| 30 |
+
|
| 31 |
+
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
|
| 32 |
2. Step 1: Find your model_id: serkanBurakOrs/ppo-SnowballTarget
|
| 33 |
3. Step 2: Select your *.nn /*.onnx file
|
| 34 |
4. Click on Watch the agent play 👀
|
SnowballTarget.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939866a89df2d5be5185b96a0905420cf0352184b199f77e585f85ffec7d5154
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-149984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c910bb69567b84ce1cc2e9a7392bb8cc895ee50a8a10b699535f0ca09b38f8b8
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-149984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23bebbb3991d202a2f6ce5e7b3619031e7114d43be564f13e4323b2738281603
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-199984.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939866a89df2d5be5185b96a0905420cf0352184b199f77e585f85ffec7d5154
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-199984.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:171254abc971716885ba28861a24533d11a5478daae28d70dcdd2b34bd4ec24a
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-200112.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:939866a89df2d5be5185b96a0905420cf0352184b199f77e585f85ffec7d5154
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-200112.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0952068cd6538593fc3563d1b0eec2ac21af7724a21cf632ecad460d248e2e03
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-49936.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5b5ae1ca818fd7cf8056914bfb5c8cb03658e13ddebd57faccadf4a8d500ce3
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-49936.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3923bba20aa82bfe4a82a7c2a9c3286ca7c54e53f1bf924d50b7194cf95478f3
|
| 3 |
size 3843968
|
SnowballTarget/SnowballTarget-99960.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 646532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08980949628ee8bdd0976a071ad17ca8ff569eb35b5ea5f2672eb7440d5cddc
|
| 3 |
size 646532
|
SnowballTarget/SnowballTarget-99960.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72c4256cc3b3e130d30a7d804cf80aada616aa126f03f23bc3a39ce5e6178bb0
|
| 3 |
size 3843968
|
SnowballTarget/checkpoint.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3843968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0952068cd6538593fc3563d1b0eec2ac21af7724a21cf632ecad460d248e2e03
|
| 3 |
size 3843968
|
SnowballTarget/events.out.tfevents.1686488744.323e160b8448.1531.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51ea6e3978cd7104901ed8368625acdb32c205d6e05bf562be7eebf7a87d55e8
|
| 3 |
+
size 23830
|
run_logs/Player-0.log
CHANGED
|
@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
|
|
| 34 |
FMOD failed to initialize the output device.: "Error initializing output device. " (60)
|
| 35 |
FMOD initialized on nosound output
|
| 36 |
Begin MonoManager ReloadAssembly
|
| 37 |
-
- Completed reload, in 0.
|
| 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
|
|
@@ -184,7 +184,7 @@ Memory Statistics:
|
|
| 184 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5461 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
|
|
@@ -213,10 +213,10 @@ 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]: 5461 frames
|
|
|
|
| 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 0.082 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: 0.666344 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 41
|
| 173 |
[ALLOC_BUCKET]
|
| 174 |
Large Block size 4.0 MB
|
| 175 |
Used Block count 1
|
|
|
|
| 184 |
Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
|
| 185 |
Requested Block Size 16.0 MB
|
| 186 |
Peak Block count 1
|
| 187 |
+
Peak Allocated memory 17.9 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]: 4645 frames, [64.0 KB-128.0 KB]: 816 frames
|
| 217 |
Requested Block Size 16.0 MB
|
| 218 |
Peak Block count 1
|
| 219 |
+
Peak Allocated memory 66.8 KB
|
| 220 |
Peak Large allocation bytes 0 B
|
| 221 |
[ALLOC_GFX_THREAD]
|
| 222 |
Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
|
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": {
|
|
@@ -26,15 +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": 1.
|
| 74 |
"count": 20
|
| 75 |
},
|
| 76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
@@ -110,27 +110,27 @@
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
-
"value": 25.
|
| 114 |
-
"min": 3.
|
| 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": 25.
|
| 126 |
-
"min": 3.
|
| 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.
|
| 153 |
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
|
| 154 |
"mlagents_version": "0.31.0.dev0",
|
| 155 |
"mlagents_envs_version": "0.31.0.dev0",
|
| 156 |
"communication_protocol_version": "1.5.0",
|
| 157 |
"pytorch_version": "1.11.0+cu102",
|
| 158 |
"numpy_version": "1.21.2",
|
| 159 |
-
"end_time_seconds": "
|
| 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":
|
| 177 |
"count": 1,
|
| 178 |
-
"self":
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
-
"total":
|
| 182 |
"count": 18203,
|
| 183 |
-
"self": 0.
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
-
"total":
|
| 187 |
"count": 18203,
|
| 188 |
-
"self":
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
-
"total":
|
| 192 |
"count": 18203,
|
| 193 |
-
"self":
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
-
"total": 124.
|
| 197 |
"count": 18203,
|
| 198 |
-
"self": 124.
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
-
"total": 0.
|
| 204 |
"count": 18203,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
-
"total":
|
| 209 |
"count": 18203,
|
| 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": 18202,
|
| 272 |
"is_parallel": true,
|
| 273 |
-
"self": 9.
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
-
"total": 5.
|
| 277 |
"count": 18202,
|
| 278 |
"is_parallel": true,
|
| 279 |
-
"self": 5.
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
-
"total":
|
| 283 |
"count": 18202,
|
| 284 |
"is_parallel": true,
|
| 285 |
-
"self":
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
-
"total":
|
| 289 |
"count": 18202,
|
| 290 |
"is_parallel": true,
|
| 291 |
-
"self": 6.
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
-
"total":
|
| 295 |
"count": 182020,
|
| 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": 10.
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
-
"total":
|
| 330 |
-
"count":
|
| 331 |
"is_parallel": true,
|
| 332 |
-
"self":
|
| 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": 4587,
|
| 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": 0.8860312104225159,
|
| 6 |
+
"min": 0.8860312104225159,
|
| 7 |
+
"max": 2.8547184467315674,
|
| 8 |
"count": 20
|
| 9 |
},
|
| 10 |
"SnowballTarget.Policy.Entropy.sum": {
|
| 11 |
+
"value": 8469.572265625,
|
| 12 |
+
"min": 8469.572265625,
|
| 13 |
+
"max": 29235.171875,
|
| 14 |
"count": 20
|
| 15 |
},
|
| 16 |
"SnowballTarget.Step.mean": {
|
|
|
|
| 26 |
"count": 20
|
| 27 |
},
|
| 28 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
+
"value": 12.401437759399414,
|
| 30 |
+
"min": 0.43631571531295776,
|
| 31 |
+
"max": 12.401437759399414,
|
| 32 |
"count": 20
|
| 33 |
},
|
| 34 |
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
+
"value": 2418.2802734375,
|
| 36 |
+
"min": 84.64524841308594,
|
| 37 |
+
"max": 2469.08642578125,
|
| 38 |
"count": 20
|
| 39 |
},
|
| 40 |
"SnowballTarget.Environment.EpisodeLength.mean": {
|
|
|
|
| 50 |
"count": 20
|
| 51 |
},
|
| 52 |
"SnowballTarget.Losses.PolicyLoss.mean": {
|
| 53 |
+
"value": 0.06929926320541804,
|
| 54 |
+
"min": 0.06106660047896416,
|
| 55 |
+
"max": 0.07362245074317815,
|
| 56 |
"count": 20
|
| 57 |
},
|
| 58 |
"SnowballTarget.Losses.PolicyLoss.sum": {
|
| 59 |
+
"value": 0.2771970528216722,
|
| 60 |
+
"min": 0.2522543780474984,
|
| 61 |
+
"max": 0.3626175124987711,
|
| 62 |
"count": 20
|
| 63 |
},
|
| 64 |
"SnowballTarget.Losses.ValueLoss.mean": {
|
| 65 |
+
"value": 0.20916674607524685,
|
| 66 |
+
"min": 0.12856522972773138,
|
| 67 |
+
"max": 0.2808943573166342,
|
| 68 |
"count": 20
|
| 69 |
},
|
| 70 |
"SnowballTarget.Losses.ValueLoss.sum": {
|
| 71 |
+
"value": 0.8366669843009874,
|
| 72 |
+
"min": 0.5142609189109255,
|
| 73 |
+
"max": 1.404471786583171,
|
| 74 |
"count": 20
|
| 75 |
},
|
| 76 |
"SnowballTarget.Policy.LearningRate.mean": {
|
|
|
|
| 110 |
"count": 20
|
| 111 |
},
|
| 112 |
"SnowballTarget.Environment.CumulativeReward.mean": {
|
| 113 |
+
"value": 25.15909090909091,
|
| 114 |
+
"min": 3.5454545454545454,
|
| 115 |
+
"max": 25.15909090909091,
|
| 116 |
"count": 20
|
| 117 |
},
|
| 118 |
"SnowballTarget.Environment.CumulativeReward.sum": {
|
| 119 |
+
"value": 1107.0,
|
| 120 |
+
"min": 156.0,
|
| 121 |
+
"max": 1360.0,
|
| 122 |
"count": 20
|
| 123 |
},
|
| 124 |
"SnowballTarget.Policy.ExtrinsicReward.mean": {
|
| 125 |
+
"value": 25.15909090909091,
|
| 126 |
+
"min": 3.5454545454545454,
|
| 127 |
+
"max": 25.15909090909091,
|
| 128 |
"count": 20
|
| 129 |
},
|
| 130 |
"SnowballTarget.Policy.ExtrinsicReward.sum": {
|
| 131 |
+
"value": 1107.0,
|
| 132 |
+
"min": 156.0,
|
| 133 |
+
"max": 1360.0,
|
| 134 |
"count": 20
|
| 135 |
},
|
| 136 |
"SnowballTarget.IsTraining.mean": {
|
|
|
|
| 148 |
},
|
| 149 |
"metadata": {
|
| 150 |
"timer_format_version": "0.1.0",
|
| 151 |
+
"start_time_seconds": "1686488743",
|
| 152 |
+
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
|
| 153 |
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
|
| 154 |
"mlagents_version": "0.31.0.dev0",
|
| 155 |
"mlagents_envs_version": "0.31.0.dev0",
|
| 156 |
"communication_protocol_version": "1.5.0",
|
| 157 |
"pytorch_version": "1.11.0+cu102",
|
| 158 |
"numpy_version": "1.21.2",
|
| 159 |
+
"end_time_seconds": "1686489219"
|
| 160 |
},
|
| 161 |
+
"total": 475.712537186,
|
| 162 |
"count": 1,
|
| 163 |
+
"self": 0.38365829800005713,
|
| 164 |
"children": {
|
| 165 |
"run_training.setup": {
|
| 166 |
+
"total": 0.04212836400000697,
|
| 167 |
"count": 1,
|
| 168 |
+
"self": 0.04212836400000697
|
| 169 |
},
|
| 170 |
"TrainerController.start_learning": {
|
| 171 |
+
"total": 475.28675052399996,
|
| 172 |
"count": 1,
|
| 173 |
+
"self": 0.6000244030034878,
|
| 174 |
"children": {
|
| 175 |
"TrainerController._reset_env": {
|
| 176 |
+
"total": 4.0133400439999605,
|
| 177 |
"count": 1,
|
| 178 |
+
"self": 4.0133400439999605
|
| 179 |
},
|
| 180 |
"TrainerController.advance": {
|
| 181 |
+
"total": 470.5411099679965,
|
| 182 |
"count": 18203,
|
| 183 |
+
"self": 0.2956814329763233,
|
| 184 |
"children": {
|
| 185 |
"env_step": {
|
| 186 |
+
"total": 470.24542853502015,
|
| 187 |
"count": 18203,
|
| 188 |
+
"self": 343.2098262260198,
|
| 189 |
"children": {
|
| 190 |
"SubprocessEnvManager._take_step": {
|
| 191 |
+
"total": 126.74192283399861,
|
| 192 |
"count": 18203,
|
| 193 |
+
"self": 1.8255496789951735,
|
| 194 |
"children": {
|
| 195 |
"TorchPolicy.evaluate": {
|
| 196 |
+
"total": 124.91637315500344,
|
| 197 |
"count": 18203,
|
| 198 |
+
"self": 124.91637315500344
|
| 199 |
}
|
| 200 |
}
|
| 201 |
},
|
| 202 |
"workers": {
|
| 203 |
+
"total": 0.2936794750017384,
|
| 204 |
"count": 18203,
|
| 205 |
"self": 0.0,
|
| 206 |
"children": {
|
| 207 |
"worker_root": {
|
| 208 |
+
"total": 473.58662686099785,
|
| 209 |
"count": 18203,
|
| 210 |
"is_parallel": true,
|
| 211 |
+
"self": 218.97701059199898,
|
| 212 |
"children": {
|
| 213 |
"run_training.setup": {
|
| 214 |
"total": 0.0,
|
|
|
|
| 217 |
"self": 0.0,
|
| 218 |
"children": {
|
| 219 |
"steps_from_proto": {
|
| 220 |
+
"total": 0.004993671000022459,
|
| 221 |
"count": 1,
|
| 222 |
"is_parallel": true,
|
| 223 |
+
"self": 0.0034961370000132774,
|
| 224 |
"children": {
|
| 225 |
"_process_rank_one_or_two_observation": {
|
| 226 |
+
"total": 0.001497534000009182,
|
| 227 |
"count": 10,
|
| 228 |
"is_parallel": true,
|
| 229 |
+
"self": 0.001497534000009182
|
| 230 |
}
|
| 231 |
}
|
| 232 |
},
|
| 233 |
"UnityEnvironment.step": {
|
| 234 |
+
"total": 0.0460440100000028,
|
| 235 |
"count": 1,
|
| 236 |
"is_parallel": true,
|
| 237 |
+
"self": 0.0005654870000171286,
|
| 238 |
"children": {
|
| 239 |
"UnityEnvironment._generate_step_input": {
|
| 240 |
+
"total": 0.00030069799998955205,
|
| 241 |
"count": 1,
|
| 242 |
"is_parallel": true,
|
| 243 |
+
"self": 0.00030069799998955205
|
| 244 |
},
|
| 245 |
"communicator.exchange": {
|
| 246 |
+
"total": 0.04301984500000344,
|
| 247 |
"count": 1,
|
| 248 |
"is_parallel": true,
|
| 249 |
+
"self": 0.04301984500000344
|
| 250 |
},
|
| 251 |
"steps_from_proto": {
|
| 252 |
+
"total": 0.0021579799999926763,
|
| 253 |
"count": 1,
|
| 254 |
"is_parallel": true,
|
| 255 |
+
"self": 0.00037325000005239417,
|
| 256 |
"children": {
|
| 257 |
"_process_rank_one_or_two_observation": {
|
| 258 |
+
"total": 0.0017847299999402821,
|
| 259 |
"count": 10,
|
| 260 |
"is_parallel": true,
|
| 261 |
+
"self": 0.0017847299999402821
|
| 262 |
}
|
| 263 |
}
|
| 264 |
}
|
|
|
|
| 267 |
}
|
| 268 |
},
|
| 269 |
"UnityEnvironment.step": {
|
| 270 |
+
"total": 254.60961626899888,
|
| 271 |
"count": 18202,
|
| 272 |
"is_parallel": true,
|
| 273 |
+
"self": 9.950199223993877,
|
| 274 |
"children": {
|
| 275 |
"UnityEnvironment._generate_step_input": {
|
| 276 |
+
"total": 5.308905314002402,
|
| 277 |
"count": 18202,
|
| 278 |
"is_parallel": true,
|
| 279 |
+
"self": 5.308905314002402
|
| 280 |
},
|
| 281 |
"communicator.exchange": {
|
| 282 |
+
"total": 205.67245253699713,
|
| 283 |
"count": 18202,
|
| 284 |
"is_parallel": true,
|
| 285 |
+
"self": 205.67245253699713
|
| 286 |
},
|
| 287 |
"steps_from_proto": {
|
| 288 |
+
"total": 33.67805919400547,
|
| 289 |
"count": 18202,
|
| 290 |
"is_parallel": true,
|
| 291 |
+
"self": 6.583394628998633,
|
| 292 |
"children": {
|
| 293 |
"_process_rank_one_or_two_observation": {
|
| 294 |
+
"total": 27.094664565006838,
|
| 295 |
"count": 182020,
|
| 296 |
"is_parallel": true,
|
| 297 |
+
"self": 27.094664565006838
|
| 298 |
}
|
| 299 |
}
|
| 300 |
}
|
|
|
|
| 309 |
}
|
| 310 |
},
|
| 311 |
"trainer_threads": {
|
| 312 |
+
"total": 0.00012717300000986143,
|
| 313 |
"count": 1,
|
| 314 |
+
"self": 0.00012717300000986143,
|
| 315 |
"children": {
|
| 316 |
"thread_root": {
|
| 317 |
"total": 0.0,
|
|
|
|
| 320 |
"self": 0.0,
|
| 321 |
"children": {
|
| 322 |
"trainer_advance": {
|
| 323 |
+
"total": 466.88163048496557,
|
| 324 |
+
"count": 465441,
|
| 325 |
"is_parallel": true,
|
| 326 |
+
"self": 10.076395576984055,
|
| 327 |
"children": {
|
| 328 |
"process_trajectory": {
|
| 329 |
+
"total": 256.432567695982,
|
| 330 |
+
"count": 465441,
|
| 331 |
"is_parallel": true,
|
| 332 |
+
"self": 255.20579185698193,
|
| 333 |
"children": {
|
| 334 |
"RLTrainer._checkpoint": {
|
| 335 |
+
"total": 1.2267758390000836,
|
| 336 |
"count": 4,
|
| 337 |
"is_parallel": true,
|
| 338 |
+
"self": 1.2267758390000836
|
| 339 |
}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
"_update_policy": {
|
| 343 |
+
"total": 200.3726672119995,
|
| 344 |
"count": 90,
|
| 345 |
"is_parallel": true,
|
| 346 |
+
"self": 74.59332602600608,
|
| 347 |
"children": {
|
| 348 |
"TorchPPOOptimizer.update": {
|
| 349 |
+
"total": 125.77934118599342,
|
| 350 |
"count": 4587,
|
| 351 |
"is_parallel": true,
|
| 352 |
+
"self": 125.77934118599342
|
| 353 |
}
|
| 354 |
}
|
| 355 |
}
|
|
|
|
| 360 |
}
|
| 361 |
},
|
| 362 |
"TrainerController._save_models": {
|
| 363 |
+
"total": 0.13214893600002142,
|
| 364 |
"count": 1,
|
| 365 |
+
"self": 0.0008774120000225594,
|
| 366 |
"children": {
|
| 367 |
"RLTrainer._checkpoint": {
|
| 368 |
+
"total": 0.13127152399999886,
|
| 369 |
"count": 1,
|
| 370 |
+
"self": 0.13127152399999886
|
| 371 |
}
|
| 372 |
}
|
| 373 |
}
|
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":
|
| 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":
|
| 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": 13.545454545454545,
|
| 8 |
+
"creation_time": 1686488865.6682534,
|
| 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": 20.181818181818183,
|
| 17 |
+
"creation_time": 1686488983.6479273,
|
| 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": 23.181818181818183,
|
| 26 |
+
"creation_time": 1686489100.5036135,
|
| 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": 24.272727272727273,
|
| 35 |
+
"creation_time": 1686489219.092746,
|
| 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": 24.272727272727273,
|
| 44 |
+
"creation_time": 1686489219.253513,
|
| 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": 24.272727272727273,
|
| 54 |
+
"creation_time": 1686489219.253513,
|
| 55 |
"auxillary_file_paths": [
|
| 56 |
"results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
|
| 57 |
]
|