Animation engine for explanatory math videos

Implementation of Proximal Meta-Policy Search (ProMP) as well as related Meta-RL algorithm. Includes a useful experiment framework for Meta-RL.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Repo to reproduce the First-Explore paper results

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

code release for URDFormer

🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch

Evolutionary Computation: A Modern Perspective ---> This is a free online book, which is actively updated now (from 2023 to 2027).

Implementation of RPPO(Risk-sensitive PPO) and RPBT(Population-based self-play with RPPO)

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

PyTorch implementation of Risk-Averse Policy Learning

Real-World RL Benchmark Suite

ReDMan is an open-source simulation platform that provides a standardized implementation of safe RL algorithms for Reliable Dexterous Manipulation.

Code for Rapid Locomotion via Reinforcement Learning

Open-source reinforcement learning environment for autonomous racing — featured as a conference paper at ICCV 2021 and as the official challenge tracks at both SL4AD@ICML2022 and AI4AD@IJCAI2022. T…

Collection of Deep Reinforcement Learning Algorithms implemented in PyTorch.

Awesome Open-ended AI

A Modular Library for Off-Policy Reinforcement Learning with a focus on SafeRL and distributed computing

A simple probabilistic programming language.

Multi-Objective Reinforcement Learning algorithms implementations.

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method

Source code for our paper "Sim-to-real reinforcement learning applied to end-to-end vehicle control"

Code for the paper "Uncertainty-Driven Exploration for Generalization in Reinforcement Learning".

A goal-driven autonomous exploration through deep reinforcement learning (ICRA 2022) system that combines reactive and planned robot navigation in unknown environments

Our version of #Exploration: A Study of Count-Based Explorationfor Deep Reinforcement Learning for a class project

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven explora…

Implementations of SAILR, PDO, and CSC