https://github.com/pythonlessons/rockrl
Reinforcement Learning library for public
https://github.com/pythonlessons/rockrl
Last synced: 8 months ago
JSON representation
Reinforcement Learning library for public
- Host: GitHub
- URL: https://github.com/pythonlessons/rockrl
- Owner: pythonlessons
- License: mit
- Created: 2023-04-24T18:47:21.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-04T11:26:34.000Z (over 1 year ago)
- Last Synced: 2025-04-25T23:46:37.018Z (8 months ago)
- Language: Python
- Size: 1.21 MB
- Stars: 6
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
README
# RockRL
Reinforcement Learning library for public, for now, it only supports **TensorFlow**.
# Installation
```bash
pip install rockrl
```
# Environment requirements
RL algorithms are implemented to support `gymnasium==0.29.1` version. Main requirements are that:
- `env.reset()` would return `state` and `info` states.
- `env.step(action)` would return `state`, `reward`, `terminated`, `truncated`, `info` states.
# Supported Algorithms
- [x] PPO (Discrete and Continuous)
# Code Examples
## Proximal Policy Optimization (PPO):
- [```RockRL/tensorflow/examples/ppo/LunarLander-v2/LunarLander-v2.py```](https://github.com/pythonlessons/RockRL/tree/main/rockrl/tensorflow/examples/ppo/LunarLander-v2) is an example of using PPO to solve LunarLander-v2 (Discrete) environment.
- [```RockRL/tensorflow/examples/ppo/BipedalWalker-v3/BipedalWalker-v3.py```](https://github.com/pythonlessons/RockRL/tree/main/rockrl/tensorflow/examples/ppo/BipedalWalker-v3) is an example of using PPO to solve BipedalWalker-v2 (Continuous) environment.
- [```RockRL/tensorflow/examples/ppo/BipedalWalkerHardcore-v3/BipedalWalkerHardcore-v3.py```](https://github.com/pythonlessons/RockRL/tree/main/rockrl/tensorflow/examples/ppo/BipedalWalkerHardcore-v3) is an example of using PPO to solve BipedalWalker-v3 Hardcore (Continuous) environment.