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.
A framework for Reinforcement Learning research.
| Date | Stars |
|---|---|
| 2026-07-31 | 271 |
| 2026-08-04 | 273 |
| 2026-08-06 | 273 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<img src="docs/assets/images/logo_no_background.png" align="right" width="25%"/>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/images/readme_title_dark.svg">
<source media="(prefers-color-scheme: light)" srcset="docs/assets/images/readme_title_light.svg">
<img src="docs/assets/images/readme_title_light.svg" alt="RL-X" height="52">
</picture><br>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/images/readme_separator_2px_native_dark.svg">
<source media="(prefers-color-scheme: light)" srcset="docs/assets/images/readme_separator_2px_native_light.svg">
<img src="docs/assets/images/readme_separator_2px_native_light.svg" alt="" width="72%" height="2" align="top">
</picture>
A framework for Reinforcement Learning research.
│ [Overview](#overview) │ [Getting Started](#getting-started) │ [Documentation](https://nico-bohlinger.github.io/RL-X/) │ [Citation](#citation) │
## Overview
### Highlights
- 💡 **Perfect to understand and prototype algorithms**:
- One algorithm = One directory -> No backtracking through parent classes
- Algorithms can be easily copied out of RL-X
- ⚒️ **Known DL libraries**: Implementations in PyTorch and JAX
- ⚡ **Maximum speed**: Just-In-Time (JIT) compilation and parallel environments
- 🧪 **Mix and match and extend**: Generic interfaces between algorithms and environments
- ⛰️ **Custom environments**: Examples for MuJoCo, Isaac Lab, ManiSkill or custom socket communication
- 🚀 **GPU environments**: MJX, Warp, Isaac Lab and ManiSkill can run thousands of parallel environments
- 🤖 **Robot learning**: Training and deployment for the Unitree Go2 (quadruped) and G1 (humanoid) robots
- ⚽ **RoboCup**: Training for the RoboCup soccer competition in MuJoCo and MJX
- 🕰️ **Memory architectures**: PPO with GRU, LSTM, Transformer, History Window, Mamba-2, Memory Actions
- 📈 **Experiments**: Checkpoints, Evaluation, Console log, Tensorboard, Weights & Biases, SLURM, Docker
### Implemented Algorithms
- [Proximal Policy Optimization (PPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo)
- [Proximal Policy Optimization + Differentiable Trust Region Layers (PPO+DTRL)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_dtrl)
- [Proximal Policy Optimization + Gated Recurrent Unit (PPO+GRU)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_gru)
- [Proximal Policy Optimization + Long Short-Term Memory (PPO+LSTM)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_lstm)
- [Proximal Policy Optimization + Transformer (PPO+Transformer)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_transformer)
- [Proximal Policy Optimization + History Window (PPO+HistoryWindow)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_history_window)
- [Proximal Policy Optimization + Mamba-2 (PPO+Mamba-2)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_mamba2)
- [Proximal Policy Optimization + Memory Actions (PPO+MemoryActions)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/ppo_memory_actions)
- [Early Stopping Policy Optimization (ESPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/espo)
- [Trust Region Policy Optimization (TRPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/trpo)
- [Simple Policy Optimization (SPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/spo)
- [Flow Policy Optimization (FPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/fpo)
- [Diffusion Policy Policy Optimization (DPPO)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/dppo)
- [Diffusion Models for Maximum Entropy Reinforcement Learning (DIME)](https://github.com/nico-bohlinger/RL-X/blob/master/rl_x/algorithms/dime)
- [Relative Entropy Pathwise Policy Optimization (REPPO)](https://github.com/nico-bohlinger/RL-X/Excerpt of 10,323 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:edaa63ccd9bdd17f, topic:reinforcement-learning, desc:reinforcement learning