Commit ·
d502397
1
Parent(s): 516accc
default parameters training
Browse files- .gitattributes +1 -0
- GridFoodCollector/GridFoodCollector-1499960.onnx +3 -0
- GridFoodCollector/GridFoodCollector-1499960.pt +3 -0
- GridFoodCollector/GridFoodCollector-1999960.onnx +3 -0
- GridFoodCollector/GridFoodCollector-1999960.pt +3 -0
- GridFoodCollector/GridFoodCollector-2001280.onnx +3 -0
- GridFoodCollector/GridFoodCollector-2001280.pt +3 -0
- GridFoodCollector/GridFoodCollector-499960.onnx +3 -0
- GridFoodCollector/GridFoodCollector-499960.pt +3 -0
- GridFoodCollector/GridFoodCollector-999960.onnx +3 -0
- GridFoodCollector/GridFoodCollector-999960.pt +3 -0
- GridFoodCollector/checkpoint.pt +3 -0
- GridFoodCollector/events.out.tfevents.1657957631.Joydeeps-MacBook-Pro.local.69716.0 +3 -0
- GridFoodCollector_v1.onnx +3 -0
- README.md +31 -0
- config.json +1 -0
- configuration.yaml +75 -0
- run_logs/Player-0.log +3 -0
- run_logs/timers.json +387 -0
- run_logs/training_status.json +65 -0
.gitattributes
CHANGED
|
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
run_logs/Player-0.log filter=lfs diff=lfs merge=lfs -text
|
GridFoodCollector/GridFoodCollector-1499960.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1dab0701796d0392f7986ab316fecc1ca03e337fc661afb49f06eec9df7a005
|
| 3 |
+
size 621991
|
GridFoodCollector/GridFoodCollector-1499960.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00c1576efcab2b9d038f5071669dcd9132f27ddf4f79beb056a1a46ecc4dcfa0
|
| 3 |
+
size 3724007
|
GridFoodCollector/GridFoodCollector-1999960.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb3d519a270d68a095bed2a5a12d13b6666f64e5073615f25b41979db20fcdba
|
| 3 |
+
size 621991
|
GridFoodCollector/GridFoodCollector-1999960.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6747ed7d7fac49da99be2f0c18bcd6a1a1494c41e0d8e317702e685ec9a828bf
|
| 3 |
+
size 3724007
|
GridFoodCollector/GridFoodCollector-2001280.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb3d519a270d68a095bed2a5a12d13b6666f64e5073615f25b41979db20fcdba
|
| 3 |
+
size 621991
|
GridFoodCollector/GridFoodCollector-2001280.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8af7e202d591fed4c81ea1e54a0bfdd120e85a2338967635149ca052d933d28
|
| 3 |
+
size 3724007
|
GridFoodCollector/GridFoodCollector-499960.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f88d7c676cad9306719a896c5f9a485860bd3546b0cd81c376a0e5fb52c221d3
|
| 3 |
+
size 621991
|
GridFoodCollector/GridFoodCollector-499960.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a330c853a86306ee117601cdf583b6e6a4106720b662e89bddde272bb6300674
|
| 3 |
+
size 3724007
|
GridFoodCollector/GridFoodCollector-999960.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2114b63585674e14c1764939491319bbe10970e114ccfe98cc4234ab2cecce5f
|
| 3 |
+
size 621991
|
GridFoodCollector/GridFoodCollector-999960.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b52e90a8b5717ab4824bf34c7b6d54e9ba8faa6ffa433954b33415ecfdb4b15
|
| 3 |
+
size 3724007
|
GridFoodCollector/checkpoint.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8af7e202d591fed4c81ea1e54a0bfdd120e85a2338967635149ca052d933d28
|
| 3 |
+
size 3724007
|
GridFoodCollector/events.out.tfevents.1657957631.Joydeeps-MacBook-Pro.local.69716.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4eed0001d38d46f511b6913508a27356eda345f1d9703bf63b544dfbab4340d
|
| 3 |
+
size 248976
|
GridFoodCollector_v1.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb3d519a270d68a095bed2a5a12d13b6666f64e5073615f25b41979db20fcdba
|
| 3 |
+
size 621991
|
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- unity-ml-agents
|
| 5 |
+
- ml-agents
|
| 6 |
+
- deep-reinforcement-learning
|
| 7 |
+
- reinforcement-learning
|
| 8 |
+
- ML-Agents-GridFoodCollector
|
| 9 |
+
library_name: ml-agents
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# **ppo** Agent playing **GridFoodCollector**
|
| 13 |
+
This is a trained model of a **ppo** agent playing **GridFoodCollector** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
|
| 14 |
+
|
| 15 |
+
## Usage (with ML-Agents)
|
| 16 |
+
The Documentation: https://github.com/huggingface/ml-agents#get-started
|
| 17 |
+
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
### Resume the training
|
| 21 |
+
```
|
| 22 |
+
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
| 23 |
+
```
|
| 24 |
+
### Watch your Agent play
|
| 25 |
+
You can watch your agent **playing directly in your browser:**.
|
| 26 |
+
|
| 27 |
+
1. Go to https://huggingface.co/spaces/unity/ML-Agents-GridFoodCollector
|
| 28 |
+
2. Step 1: Write your model_id: infinitejoy/MLAgents-GridFoodCollector
|
| 29 |
+
3. Step 2: Select your *.nn /*.onnx file
|
| 30 |
+
4. Click on Watch the agent play 👀
|
| 31 |
+
|
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"default_settings": null, "behaviors": {"GridFoodCollector": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 1, "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": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/macos/food_collector/food_collector", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "firstFoodCollectorRun", "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
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_settings: null
|
| 2 |
+
behaviors:
|
| 3 |
+
GridFoodCollector:
|
| 4 |
+
trainer_type: ppo
|
| 5 |
+
hyperparameters:
|
| 6 |
+
batch_size: 1024
|
| 7 |
+
buffer_size: 10240
|
| 8 |
+
learning_rate: 0.0003
|
| 9 |
+
beta: 0.005
|
| 10 |
+
epsilon: 0.2
|
| 11 |
+
lambd: 0.95
|
| 12 |
+
num_epoch: 3
|
| 13 |
+
learning_rate_schedule: linear
|
| 14 |
+
beta_schedule: linear
|
| 15 |
+
epsilon_schedule: linear
|
| 16 |
+
network_settings:
|
| 17 |
+
normalize: false
|
| 18 |
+
hidden_units: 256
|
| 19 |
+
num_layers: 1
|
| 20 |
+
vis_encode_type: simple
|
| 21 |
+
memory: null
|
| 22 |
+
goal_conditioning_type: hyper
|
| 23 |
+
deterministic: false
|
| 24 |
+
reward_signals:
|
| 25 |
+
extrinsic:
|
| 26 |
+
gamma: 0.99
|
| 27 |
+
strength: 1.0
|
| 28 |
+
network_settings:
|
| 29 |
+
normalize: false
|
| 30 |
+
hidden_units: 128
|
| 31 |
+
num_layers: 2
|
| 32 |
+
vis_encode_type: simple
|
| 33 |
+
memory: null
|
| 34 |
+
goal_conditioning_type: hyper
|
| 35 |
+
deterministic: false
|
| 36 |
+
init_path: null
|
| 37 |
+
keep_checkpoints: 5
|
| 38 |
+
checkpoint_interval: 500000
|
| 39 |
+
max_steps: 2000000
|
| 40 |
+
time_horizon: 64
|
| 41 |
+
summary_freq: 10000
|
| 42 |
+
threaded: false
|
| 43 |
+
self_play: null
|
| 44 |
+
behavioral_cloning: null
|
| 45 |
+
env_settings:
|
| 46 |
+
env_path: ./trained-envs-executables/macos/food_collector/food_collector
|
| 47 |
+
env_args: null
|
| 48 |
+
base_port: 5005
|
| 49 |
+
num_envs: 1
|
| 50 |
+
num_areas: 1
|
| 51 |
+
seed: -1
|
| 52 |
+
max_lifetime_restarts: 10
|
| 53 |
+
restarts_rate_limit_n: 1
|
| 54 |
+
restarts_rate_limit_period_s: 60
|
| 55 |
+
engine_settings:
|
| 56 |
+
width: 84
|
| 57 |
+
height: 84
|
| 58 |
+
quality_level: 5
|
| 59 |
+
time_scale: 20
|
| 60 |
+
target_frame_rate: -1
|
| 61 |
+
capture_frame_rate: 60
|
| 62 |
+
no_graphics: true
|
| 63 |
+
environment_parameters: null
|
| 64 |
+
checkpoint_settings:
|
| 65 |
+
run_id: firstFoodCollectorRun
|
| 66 |
+
initialize_from: null
|
| 67 |
+
load_model: false
|
| 68 |
+
resume: false
|
| 69 |
+
force: false
|
| 70 |
+
train_model: false
|
| 71 |
+
inference: false
|
| 72 |
+
results_dir: results
|
| 73 |
+
torch_settings:
|
| 74 |
+
device: null
|
| 75 |
+
debug: false
|
run_logs/Player-0.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bb87a5401f2cbfea021095290e223f742a860688c21ba57c4124165e15d0b56
|
| 3 |
+
size 25658341
|
run_logs/timers.json
ADDED
|
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "root",
|
| 3 |
+
"gauges": {
|
| 4 |
+
"GridFoodCollector.Policy.Entropy.mean": {
|
| 5 |
+
"value": 1.359848141670227,
|
| 6 |
+
"min": 1.3515808582305908,
|
| 7 |
+
"max": 2.115565538406372,
|
| 8 |
+
"count": 200
|
| 9 |
+
},
|
| 10 |
+
"GridFoodCollector.Policy.Entropy.sum": {
|
| 11 |
+
"value": 13272.1181640625,
|
| 12 |
+
"min": 13191.4296875,
|
| 13 |
+
"max": 21663.390625,
|
| 14 |
+
"count": 200
|
| 15 |
+
},
|
| 16 |
+
"GridFoodCollector.Step.mean": {
|
| 17 |
+
"value": 1999960.0,
|
| 18 |
+
"min": 9984.0,
|
| 19 |
+
"max": 1999960.0,
|
| 20 |
+
"count": 200
|
| 21 |
+
},
|
| 22 |
+
"GridFoodCollector.Step.sum": {
|
| 23 |
+
"value": 1999960.0,
|
| 24 |
+
"min": 9984.0,
|
| 25 |
+
"max": 1999960.0,
|
| 26 |
+
"count": 200
|
| 27 |
+
},
|
| 28 |
+
"GridFoodCollector.Policy.ExtrinsicValueEstimate.mean": {
|
| 29 |
+
"value": 4.87490177154541,
|
| 30 |
+
"min": -0.014032418839633465,
|
| 31 |
+
"max": 5.426158905029297,
|
| 32 |
+
"count": 200
|
| 33 |
+
},
|
| 34 |
+
"GridFoodCollector.Policy.ExtrinsicValueEstimate.sum": {
|
| 35 |
+
"value": 794.6090087890625,
|
| 36 |
+
"min": -2.203089714050293,
|
| 37 |
+
"max": 884.4638671875,
|
| 38 |
+
"count": 200
|
| 39 |
+
},
|
| 40 |
+
"GridFoodCollector.TotalScore.mean": {
|
| 41 |
+
"value": 0.0,
|
| 42 |
+
"min": 0.0,
|
| 43 |
+
"max": 0.0,
|
| 44 |
+
"count": 200
|
| 45 |
+
},
|
| 46 |
+
"GridFoodCollector.TotalScore.sum": {
|
| 47 |
+
"value": 0.0,
|
| 48 |
+
"min": 0.0,
|
| 49 |
+
"max": 0.0,
|
| 50 |
+
"count": 200
|
| 51 |
+
},
|
| 52 |
+
"GridFoodCollector.IsTraining.mean": {
|
| 53 |
+
"value": 1.0,
|
| 54 |
+
"min": 1.0,
|
| 55 |
+
"max": 1.0,
|
| 56 |
+
"count": 200
|
| 57 |
+
},
|
| 58 |
+
"GridFoodCollector.IsTraining.sum": {
|
| 59 |
+
"value": 1.0,
|
| 60 |
+
"min": 1.0,
|
| 61 |
+
"max": 1.0,
|
| 62 |
+
"count": 200
|
| 63 |
+
},
|
| 64 |
+
"GridFoodCollector.Losses.PolicyLoss.mean": {
|
| 65 |
+
"value": 0.025195259346880695,
|
| 66 |
+
"min": 0.01637561379854257,
|
| 67 |
+
"max": 0.03352702839765698,
|
| 68 |
+
"count": 177
|
| 69 |
+
},
|
| 70 |
+
"GridFoodCollector.Losses.PolicyLoss.sum": {
|
| 71 |
+
"value": 0.025195259346880695,
|
| 72 |
+
"min": 0.01637561379854257,
|
| 73 |
+
"max": 0.03352702839765698,
|
| 74 |
+
"count": 177
|
| 75 |
+
},
|
| 76 |
+
"GridFoodCollector.Losses.ValueLoss.mean": {
|
| 77 |
+
"value": 0.25333125257130823,
|
| 78 |
+
"min": 0.0032787797161180415,
|
| 79 |
+
"max": 0.37987768252690635,
|
| 80 |
+
"count": 177
|
| 81 |
+
},
|
| 82 |
+
"GridFoodCollector.Losses.ValueLoss.sum": {
|
| 83 |
+
"value": 0.25333125257130823,
|
| 84 |
+
"min": 0.0032787797161180415,
|
| 85 |
+
"max": 0.37987768252690635,
|
| 86 |
+
"count": 177
|
| 87 |
+
},
|
| 88 |
+
"GridFoodCollector.Policy.LearningRate.mean": {
|
| 89 |
+
"value": 1.2720995760000064e-06,
|
| 90 |
+
"min": 1.2720995760000064e-06,
|
| 91 |
+
"max": 0.000298272000576,
|
| 92 |
+
"count": 177
|
| 93 |
+
},
|
| 94 |
+
"GridFoodCollector.Policy.LearningRate.sum": {
|
| 95 |
+
"value": 1.2720995760000064e-06,
|
| 96 |
+
"min": 1.2720995760000064e-06,
|
| 97 |
+
"max": 0.000298272000576,
|
| 98 |
+
"count": 177
|
| 99 |
+
},
|
| 100 |
+
"GridFoodCollector.Policy.Epsilon.mean": {
|
| 101 |
+
"value": 0.10042400000000001,
|
| 102 |
+
"min": 0.10042400000000001,
|
| 103 |
+
"max": 0.19942400000000002,
|
| 104 |
+
"count": 177
|
| 105 |
+
},
|
| 106 |
+
"GridFoodCollector.Policy.Epsilon.sum": {
|
| 107 |
+
"value": 0.10042400000000001,
|
| 108 |
+
"min": 0.10042400000000001,
|
| 109 |
+
"max": 0.19942400000000002,
|
| 110 |
+
"count": 177
|
| 111 |
+
},
|
| 112 |
+
"GridFoodCollector.Policy.Beta.mean": {
|
| 113 |
+
"value": 3.115760000000011e-05,
|
| 114 |
+
"min": 3.115760000000011e-05,
|
| 115 |
+
"max": 0.0049712576,
|
| 116 |
+
"count": 177
|
| 117 |
+
},
|
| 118 |
+
"GridFoodCollector.Policy.Beta.sum": {
|
| 119 |
+
"value": 3.115760000000011e-05,
|
| 120 |
+
"min": 3.115760000000011e-05,
|
| 121 |
+
"max": 0.0049712576,
|
| 122 |
+
"count": 177
|
| 123 |
+
},
|
| 124 |
+
"GridFoodCollector.Environment.EpisodeLength.mean": {
|
| 125 |
+
"value": 999.0,
|
| 126 |
+
"min": 999.0,
|
| 127 |
+
"max": 999.0,
|
| 128 |
+
"count": 100
|
| 129 |
+
},
|
| 130 |
+
"GridFoodCollector.Environment.EpisodeLength.sum": {
|
| 131 |
+
"value": 19980.0,
|
| 132 |
+
"min": 19980.0,
|
| 133 |
+
"max": 19980.0,
|
| 134 |
+
"count": 100
|
| 135 |
+
},
|
| 136 |
+
"GridFoodCollector.Environment.CumulativeReward.mean": {
|
| 137 |
+
"value": 47.578947368421055,
|
| 138 |
+
"min": -1.0,
|
| 139 |
+
"max": 70.0,
|
| 140 |
+
"count": 199
|
| 141 |
+
},
|
| 142 |
+
"GridFoodCollector.Environment.CumulativeReward.sum": {
|
| 143 |
+
"value": 904.0,
|
| 144 |
+
"min": -3.0,
|
| 145 |
+
"max": 1059.0,
|
| 146 |
+
"count": 199
|
| 147 |
+
},
|
| 148 |
+
"GridFoodCollector.Policy.ExtrinsicReward.mean": {
|
| 149 |
+
"value": 47.578947368421055,
|
| 150 |
+
"min": -1.0,
|
| 151 |
+
"max": 70.0,
|
| 152 |
+
"count": 199
|
| 153 |
+
},
|
| 154 |
+
"GridFoodCollector.Policy.ExtrinsicReward.sum": {
|
| 155 |
+
"value": 904.0,
|
| 156 |
+
"min": -3.0,
|
| 157 |
+
"max": 1059.0,
|
| 158 |
+
"count": 199
|
| 159 |
+
}
|
| 160 |
+
},
|
| 161 |
+
"metadata": {
|
| 162 |
+
"timer_format_version": "0.1.0",
|
| 163 |
+
"start_time_seconds": "1657957629",
|
| 164 |
+
"python_version": "3.8.13 (default, Mar 28 2022, 06:16:26) \n[Clang 12.0.0 ]",
|
| 165 |
+
"command_line_arguments": "/usr/local/Caskroom/miniconda/base/envs/ml-agents/bin/mlagents-learn ./config/ppo/FoodCollector.yaml --run-id=firstFoodCollectorRun --env=./trained-envs-executables/macos/food_collector/food_collector --no-graphics",
|
| 166 |
+
"mlagents_version": "0.29.0.dev0",
|
| 167 |
+
"mlagents_envs_version": "0.29.0.dev0",
|
| 168 |
+
"communication_protocol_version": "1.5.0",
|
| 169 |
+
"pytorch_version": "1.8.1",
|
| 170 |
+
"numpy_version": "1.22.3",
|
| 171 |
+
"end_time_seconds": "1657966147"
|
| 172 |
+
},
|
| 173 |
+
"total": 8517.81745198,
|
| 174 |
+
"count": 1,
|
| 175 |
+
"self": 3.3078957159996207,
|
| 176 |
+
"children": {
|
| 177 |
+
"run_training.setup": {
|
| 178 |
+
"total": 0.14826226499999962,
|
| 179 |
+
"count": 1,
|
| 180 |
+
"self": 0.14826226499999962
|
| 181 |
+
},
|
| 182 |
+
"TrainerController.start_learning": {
|
| 183 |
+
"total": 8514.361293999,
|
| 184 |
+
"count": 1,
|
| 185 |
+
"self": 1.783625482039497,
|
| 186 |
+
"children": {
|
| 187 |
+
"TrainerController._reset_env": {
|
| 188 |
+
"total": 2.5819171579999995,
|
| 189 |
+
"count": 1,
|
| 190 |
+
"self": 2.5819171579999995
|
| 191 |
+
},
|
| 192 |
+
"TrainerController.advance": {
|
| 193 |
+
"total": 8509.88345904396,
|
| 194 |
+
"count": 100064,
|
| 195 |
+
"self": 1.8531979768140445,
|
| 196 |
+
"children": {
|
| 197 |
+
"env_step": {
|
| 198 |
+
"total": 6631.421555831045,
|
| 199 |
+
"count": 100064,
|
| 200 |
+
"self": 6445.835940382118,
|
| 201 |
+
"children": {
|
| 202 |
+
"SubprocessEnvManager._take_step": {
|
| 203 |
+
"total": 183.89434125803314,
|
| 204 |
+
"count": 100064,
|
| 205 |
+
"self": 5.59647924999382,
|
| 206 |
+
"children": {
|
| 207 |
+
"TorchPolicy.evaluate": {
|
| 208 |
+
"total": 178.29786200803932,
|
| 209 |
+
"count": 100064,
|
| 210 |
+
"self": 26.467189385055292,
|
| 211 |
+
"children": {
|
| 212 |
+
"TorchPolicy.sample_actions": {
|
| 213 |
+
"total": 151.83067262298403,
|
| 214 |
+
"count": 100064,
|
| 215 |
+
"self": 151.83067262298403
|
| 216 |
+
}
|
| 217 |
+
}
|
| 218 |
+
}
|
| 219 |
+
}
|
| 220 |
+
},
|
| 221 |
+
"workers": {
|
| 222 |
+
"total": 1.6912741908944469,
|
| 223 |
+
"count": 100064,
|
| 224 |
+
"self": 0.0,
|
| 225 |
+
"children": {
|
| 226 |
+
"worker_root": {
|
| 227 |
+
"total": 8507.739081247075,
|
| 228 |
+
"count": 100064,
|
| 229 |
+
"is_parallel": true,
|
| 230 |
+
"self": 2346.0980035521698,
|
| 231 |
+
"children": {
|
| 232 |
+
"steps_from_proto": {
|
| 233 |
+
"total": 0.1583460480000003,
|
| 234 |
+
"count": 1,
|
| 235 |
+
"is_parallel": true,
|
| 236 |
+
"self": 0.0008975530000001619,
|
| 237 |
+
"children": {
|
| 238 |
+
"_process_maybe_compressed_observation": {
|
| 239 |
+
"total": 0.15744849500000013,
|
| 240 |
+
"count": 2,
|
| 241 |
+
"is_parallel": true,
|
| 242 |
+
"self": 0.0010337530000010808,
|
| 243 |
+
"children": {
|
| 244 |
+
"_observation_to_np_array": {
|
| 245 |
+
"total": 0.15641474199999905,
|
| 246 |
+
"count": 20,
|
| 247 |
+
"is_parallel": true,
|
| 248 |
+
"self": 0.0004524959999989697,
|
| 249 |
+
"children": {
|
| 250 |
+
"process_pixels": {
|
| 251 |
+
"total": 0.15596224600000008,
|
| 252 |
+
"count": 20,
|
| 253 |
+
"is_parallel": true,
|
| 254 |
+
"self": 0.00460534700000137,
|
| 255 |
+
"children": {
|
| 256 |
+
"image_decompress": {
|
| 257 |
+
"total": 0.1513568989999987,
|
| 258 |
+
"count": 40,
|
| 259 |
+
"is_parallel": true,
|
| 260 |
+
"self": 0.1513568989999987
|
| 261 |
+
}
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
}
|
| 265 |
+
}
|
| 266 |
+
}
|
| 267 |
+
}
|
| 268 |
+
}
|
| 269 |
+
},
|
| 270 |
+
"UnityEnvironment.step": {
|
| 271 |
+
"total": 6161.482731646905,
|
| 272 |
+
"count": 100064,
|
| 273 |
+
"is_parallel": true,
|
| 274 |
+
"self": 16.49925906266344,
|
| 275 |
+
"children": {
|
| 276 |
+
"UnityEnvironment._generate_step_input": {
|
| 277 |
+
"total": 31.14237213411976,
|
| 278 |
+
"count": 100064,
|
| 279 |
+
"is_parallel": true,
|
| 280 |
+
"self": 31.14237213411976
|
| 281 |
+
},
|
| 282 |
+
"communicator.exchange": {
|
| 283 |
+
"total": 5398.861776458055,
|
| 284 |
+
"count": 100064,
|
| 285 |
+
"is_parallel": true,
|
| 286 |
+
"self": 5398.861776458055
|
| 287 |
+
},
|
| 288 |
+
"steps_from_proto": {
|
| 289 |
+
"total": 714.9793239920671,
|
| 290 |
+
"count": 100064,
|
| 291 |
+
"is_parallel": true,
|
| 292 |
+
"self": 23.410001086074658,
|
| 293 |
+
"children": {
|
| 294 |
+
"_process_maybe_compressed_observation": {
|
| 295 |
+
"total": 691.5693229059924,
|
| 296 |
+
"count": 200128,
|
| 297 |
+
"is_parallel": true,
|
| 298 |
+
"self": 43.33982541681246,
|
| 299 |
+
"children": {
|
| 300 |
+
"_observation_to_np_array": {
|
| 301 |
+
"total": 648.22949748918,
|
| 302 |
+
"count": 2003280,
|
| 303 |
+
"is_parallel": true,
|
| 304 |
+
"self": 28.235964853949667,
|
| 305 |
+
"children": {
|
| 306 |
+
"process_pixels": {
|
| 307 |
+
"total": 619.9935326352303,
|
| 308 |
+
"count": 2003280,
|
| 309 |
+
"is_parallel": true,
|
| 310 |
+
"self": 224.81378869611558,
|
| 311 |
+
"children": {
|
| 312 |
+
"image_decompress": {
|
| 313 |
+
"total": 395.1797439391147,
|
| 314 |
+
"count": 4006560,
|
| 315 |
+
"is_parallel": true,
|
| 316 |
+
"self": 395.1797439391147
|
| 317 |
+
}
|
| 318 |
+
}
|
| 319 |
+
}
|
| 320 |
+
}
|
| 321 |
+
}
|
| 322 |
+
}
|
| 323 |
+
}
|
| 324 |
+
}
|
| 325 |
+
}
|
| 326 |
+
}
|
| 327 |
+
}
|
| 328 |
+
}
|
| 329 |
+
}
|
| 330 |
+
}
|
| 331 |
+
}
|
| 332 |
+
}
|
| 333 |
+
},
|
| 334 |
+
"trainer_advance": {
|
| 335 |
+
"total": 1876.6087052361006,
|
| 336 |
+
"count": 100064,
|
| 337 |
+
"self": 2.761222060032196,
|
| 338 |
+
"children": {
|
| 339 |
+
"process_trajectory": {
|
| 340 |
+
"total": 161.73564826707266,
|
| 341 |
+
"count": 100064,
|
| 342 |
+
"self": 161.07081238007177,
|
| 343 |
+
"children": {
|
| 344 |
+
"RLTrainer._checkpoint": {
|
| 345 |
+
"total": 0.6648358870008906,
|
| 346 |
+
"count": 4,
|
| 347 |
+
"self": 0.6648358870008906
|
| 348 |
+
}
|
| 349 |
+
}
|
| 350 |
+
},
|
| 351 |
+
"_update_policy": {
|
| 352 |
+
"total": 1712.1118349089957,
|
| 353 |
+
"count": 177,
|
| 354 |
+
"self": 264.99061731096344,
|
| 355 |
+
"children": {
|
| 356 |
+
"TorchPPOOptimizer.update": {
|
| 357 |
+
"total": 1447.1212175980322,
|
| 358 |
+
"count": 5544,
|
| 359 |
+
"self": 1447.1212175980322
|
| 360 |
+
}
|
| 361 |
+
}
|
| 362 |
+
}
|
| 363 |
+
}
|
| 364 |
+
}
|
| 365 |
+
}
|
| 366 |
+
},
|
| 367 |
+
"trainer_threads": {
|
| 368 |
+
"total": 1.035999957821332e-06,
|
| 369 |
+
"count": 1,
|
| 370 |
+
"self": 1.035999957821332e-06
|
| 371 |
+
},
|
| 372 |
+
"TrainerController._save_models": {
|
| 373 |
+
"total": 0.11229127899969171,
|
| 374 |
+
"count": 1,
|
| 375 |
+
"self": 0.0038968419994489523,
|
| 376 |
+
"children": {
|
| 377 |
+
"RLTrainer._checkpoint": {
|
| 378 |
+
"total": 0.10839443700024276,
|
| 379 |
+
"count": 1,
|
| 380 |
+
"self": 0.10839443700024276
|
| 381 |
+
}
|
| 382 |
+
}
|
| 383 |
+
}
|
| 384 |
+
}
|
| 385 |
+
}
|
| 386 |
+
}
|
| 387 |
+
}
|
run_logs/training_status.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"GridFoodCollector": {
|
| 3 |
+
"checkpoints": [
|
| 4 |
+
{
|
| 5 |
+
"steps": 499960,
|
| 6 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-499960.onnx",
|
| 7 |
+
"reward": 28.42105263157895,
|
| 8 |
+
"creation_time": 1657959557.301697,
|
| 9 |
+
"auxillary_file_paths": [
|
| 10 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-499960.pt"
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"steps": 999960,
|
| 15 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-999960.onnx",
|
| 16 |
+
"reward": 52.73684210526316,
|
| 17 |
+
"creation_time": 1657961681.560199,
|
| 18 |
+
"auxillary_file_paths": [
|
| 19 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-999960.pt"
|
| 20 |
+
]
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"steps": 1499960,
|
| 24 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-1499960.onnx",
|
| 25 |
+
"reward": 50.36842105263158,
|
| 26 |
+
"creation_time": 1657963821.9519942,
|
| 27 |
+
"auxillary_file_paths": [
|
| 28 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-1499960.pt"
|
| 29 |
+
]
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"steps": 1999960,
|
| 33 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-1999960.onnx",
|
| 34 |
+
"reward": 47.578947368421055,
|
| 35 |
+
"creation_time": 1657966139.089219,
|
| 36 |
+
"auxillary_file_paths": [
|
| 37 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-1999960.pt"
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"steps": 2001280,
|
| 42 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-2001280.onnx",
|
| 43 |
+
"reward": 47.05,
|
| 44 |
+
"creation_time": 1657966143.806728,
|
| 45 |
+
"auxillary_file_paths": [
|
| 46 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-2001280.pt"
|
| 47 |
+
]
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"final_checkpoint": {
|
| 51 |
+
"steps": 2001280,
|
| 52 |
+
"file_path": "results/firstFoodCollectorRun/GridFoodCollector.onnx",
|
| 53 |
+
"reward": 47.05,
|
| 54 |
+
"creation_time": 1657966143.806728,
|
| 55 |
+
"auxillary_file_paths": [
|
| 56 |
+
"results/firstFoodCollectorRun/GridFoodCollector/GridFoodCollector-2001280.pt"
|
| 57 |
+
]
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"metadata": {
|
| 61 |
+
"stats_format_version": "0.3.0",
|
| 62 |
+
"mlagents_version": "0.29.0.dev0",
|
| 63 |
+
"torch_version": "1.8.1"
|
| 64 |
+
}
|
| 65 |
+
}
|