Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Reinforcement Learning Algorithms Based on PyTorch
| Date | Stars |
|---|---|
| 2026-07-31 | 453 |
| 2026-08-06 | 453 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<a href="https://github.com/StepNeverStop/RLs">
<img width="auto" height="200px" src="./pics/logo.png">
</a>
<br/>
<br/>
<a href="https://github.com/StepNeverStop/RLs">
<img width="auto" height="20px" src="./pics/font.png">
</a>
</div>
<div align="center">
<p><strong>RLs:</strong> Reinforcement Learning Algorithm Based On PyTorch.</p>
</div>
# RLs
This project includes SOTA or classic reinforcement learning (single and multi-agent) algorithms used for training
agents by interacting with Unity through [ml-agents](https://github.com/Unity-Technologies/ml-agents/tree/release_18)
Release 18 or with [gym](https://github.com/openai/gym).
## About
The goal of this framework is to provide stable implementations of standard RL algorithms and simultaneously enable fast
prototyping of new methods. It aims to fill the need for a small, easily grokked codebase in which users can freely
experiment with wild ideas (speculative research).
## Characteristics
This project supports:
- Suitable for Windows, Linux, and OSX
- Single- and Multi-Agent training.
- Multiple type of observation sensors as input.
- Only need 3 steps to implement a new algorithm:
1. **policy** write `.py` in `rls/algorithms/{single/multi}` directory and make the policy inherit from super-class
defined in `rls/algorithms/base`
2. **config** write `.yaml` in `rls/configs/algorithms/` directory and specify the super config type defined
in `rls/configs/algorithms/general.yaml`
3. **register** register new algorithm in `rls/algorithms/__init__.py`
- Only need 3 steps to adapt to a new training environment:
1. **wrapper** write environment wrappers in `rls/envs/{new platform}` directory and make it inherit from
super-class defined in `rls/envs/env_base.py`
2. **config** write default configuration in `rls/configs/{new platform}`
3. **register** register new environment platform in `rls/envs/__init__.py`
- Compatible with several environment platforms
- [Unity3D ml-agents](https://github.com/Unity-Technologies/ml-agents).
- [PettingZoo](https://www.pettingzoo.ml/#)
- [gym](https://github.com/openai/gym), for now only two data types are compatible——`[Box, Discrete]`. Support
parallel training using gym envs, just need to specify `--copies` to how many agents you want to train in
parallel.
- environments:
- [MuJoCo](https://github.com/openai/mujoco-py)(v2.0.2.13)
- [PyBullet](https://github.com/bulletphysics/bullet3)
- [gym_minigrid](https://github.com/maximecb/gym-minigrid)
- observation -> action:
- Discrete -> Discrete (observation type -> action type)
- Discrete -> Box
- Box -> Discrete
- Box -> Box
- Box/Discrete -> Tuple(Discrete, Discrete, Discrete)
- Four types of Replay Buffer, Default is ER:
- ER
- [Prioritized ER](https://arxiv.org/abs/1511.05952)
- [Noisy Net](https://arxiv.org/abs/1706.10295) for better exploration.
- [Intrinsic Curiosity Module](https://arxiv.org/abs/1705.05363) for almost all off-policy algorithms implemented.
- Parallel training multiple scenes for Gym
- Unified data format
## Installation
method 1:
```bash
$ git clone https://github.com/StepNeverStop/RLs.git
$ cd RLs
$ conda create -n rls python=3.8
$ conda activate rls
# Windows
$ pip install -e .[windows]
# Linux or Mac OS
$ pip install -e .
```
method 1:
```bash
conda env create -f environment.yaml
```
If using ml-agents:
```bash
$ pip install -e .[unity]
```
You can download the builded docker image from [here](https://hub.docker.com/r/keavnn/rls):
```bash
$ docker pull keavnn/rls:latest
```
If anyone who wants to send a PR, plz format all code-files first:
```bash
$ pip install -e .[pr]
$ python auto_format.py -d ./
```
## Implemented Algorithms
Excerpt of 16,624 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:72e0f29727710313, topic:reinforcement-learning, topic:deep-reinforcement-learning, desc:reinforcement learning