Metadata-Version: 2.4
Name: minimalist-RL
Version: 0.0.6
Summary: Minimalist & Decoupled Reinforcement Learning.
Home-page: https://github.com/SerenaTradingResearch/minimalist-RL
Author: Ricky Ding
Author-email: e0134117@u.nus.edu
License: MIT
Keywords: reinforcement-learning,rl,ppo,sac,pytorch,minimalist
Classifier: Intended Audience :: Education
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: gymnasium
Requires-Dist: numpy
Requires-Dist: torch
Requires-Dist: trading_models
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary


## Intro

- `Minimalist` & `Decoupled` Reinforcement Learning

![](https://raw.githubusercontent.com/SerenaTradingResearch/minimalist-RL/main/test/SAC_HalfCheetah-v5.png)

## Usage

```bash
pip install minimalist-RL
```

```py
import gymnasium as gym
import torch.nn as nn

from minimalist_RL.SAC import SAC, ActorCritic
from minimalist_RL.utils import train_RL

env = gym.make("HalfCheetah-v5")
ac_net = ActorCritic(env, sizes=[256, 256], Act=nn.ReLU)
sac = SAC(ac_net)
train_RL(env, ac_net.pi.tanh_act, sac.update)
```
