Metadata-Version: 2.1
Name: rl_tools
Version: 0.0.1
Summary: A general toolset for reinforcement learning (RL)
Home-page: https://github.com/gxywy/rl-tools
Author: Gong Xiaoyu
Author-email: gxywy@hotmail.com
License: UNKNOWN
Description: # rl-tools
        
        ![PyPI](https://img.shields.io/pypi/v/rl-tools?style=flat-square) ![GitHub](https://img.shields.io/github/license/gxywy/rl-tools?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/gxywy/rl-tools?style=flat-square)
        
         This is a simple toolset for reinforcement learning (RL).
        
        ## Installation
        
        from PIP
        
        ```
        pip install rl_tools
        ```
        
        from source
        
        ```shell
        python setup.py install
        ```
        
        ## Usage
        
        **As a alone script:**
        
        for example:
        
        ```
        python -m rl_tools.plotter --save --show
        ```
        
        - [enjoy.py](./rl_tools/enjoy.py)  enjoy the trained model, and track avg, med, std, min, max reward of episodes.
        - [plotter.py](./rl_tools/plotter.py) plot learning curves for training , see [rl-plotter](https://github.com/gxywy/rl-plotter) for detail.
        - [scheduler.py](./rl_tools/scheduler.py)  set training scheduler for tasks.
        
        
        
        **In RL agent:**
        
        for example:
        
        ```
        from rl_tools.evaluator import Evaluator
        from rl_tools.logger import Logger
        ```
        
        - [evaluator.py](./rl_tools/evaluator.py) evaluate model while training.
        - [logger.py](./rl_tools/logger.py) track learning process while training (same format as OpenAI baseline).
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.0
Description-Content-Type: text/markdown
