This repository aims to provide the minimalism of cleanRL with the performance of SBX

A collection of useful .gitignore templates

Implementations of Multi-Task and Meta-Learning baselines for the Metaworld benchmark

JAX port of efficient-kan

Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

Neural-Lyapunov-Approximation-SACLA

Multi-task reinforcement learning research

Docker images for my ML projects

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Async Python framework optimized for IO-heavy applications.

A Rust HTTP server for Python applications

[NeurIPS VLM workshop 2024] In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding

A modern alternative to ls

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

🔥Highlighting the top ML papers every week.

My personal website

My AlphaZero implementations with Pytorch! (Game of Go; Mahjong)

Focus on time series prediction methods to solve time delay in teleoperation