Long-Term Evolution Project of Reinforcement Learning

A Multi-Task Dataset for Simulated Humanoid Control

An API conversion tool for popular external reinforcement learning environments

JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"

Explorer is a PyTorch reinforcement learning framework for exploring new ideas.

[ICML 2025 oral] Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

Official PyTorch implementation of "DC-MPC: Discrete Codebook Model Predictive Control"

(ICLR 2021) Learning to Represent Action Values as a Hypergraph on the Action Vertices

Dockerfile for RL research. Including MuJoCo / DMC / PyTorch / Tensoflow / Atari support.

Official PyTorch Implementation of Our Paper Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks

Contextual MDPs with changing rewards and dynamics, implemented based on DeepMind Control Suite

[AAMAS 2024 oral] Original PyTorch implementation of experiments in paper 'Normalization Enhances Generalization in Visual Reinforcement Learning'.

This is the code for a stochastic environment for human-in-the-loop grasping (ICRA'21).

Solving ceetah,cartpole,reacher,walker Deepmind Control Suite using DDPG (Pythorc)

Planning from Pixels with PlaNet

Clean RL algorithm implementations in under 100 lines each.

Code release for "Learning in Complex Action Spaces without Policy Gradients" TMLR (2025)

No description provided.