https://github.com/xffxff/ppo
Implementing ppo based on openai/baselines, but more readable.
https://github.com/xffxff/ppo
multiprocessing ppo reinforcement-learning
Last synced: 2 months ago
JSON representation
Implementing ppo based on openai/baselines, but more readable.
- Host: GitHub
- URL: https://github.com/xffxff/ppo
- Owner: xffxff
- License: apache-2.0
- Created: 2019-02-17T07:50:10.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-02-23T02:24:49.000Z (over 7 years ago)
- Last Synced: 2025-01-28T03:17:30.592Z (over 1 year ago)
- Topics: multiprocessing, ppo, reinforcement-learning
- Language: Python
- Homepage:
- Size: 62.5 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# PPO
## Installation
### Install [openai/baselines](https://github.com/openai/baselines.git)
```
git clone https://github.com/openai/baselines.git
cd baselines
pip install -e .
```
### Install XFFXFF/PPO
```
git clone https://github.com/XFFXFF/PPO.git
cd PPO
pip install -e .
```
### Train a Model
```
python -m ppo.run --env BreakoutNoFrameskip-v4
```