Constrained Ensemble Exploration for Unsupervised Skill Discovery

Pessimistic Value Iteration for Multi-Task Data Sharing in Offline RL

A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training

BeCL: Behavior Contrastive Learning for Unsupervised Skill Discovery.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3 BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning

Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

Dynamic Bottleneck for Robust Self-Supervised Exploration

ExORL: Exploratory Data for Offline Reinforcement Learning

Code for "Addressing Hindsight Bias in Multi-Goal Reinforcement Learning"

Code for "Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning"

PyTorch implementation of FQF, IQN and QR-DQN.

Elegant LaTeX Template for Books

Distributional Soft Actor Critic

Code for "Principled Exploration via Optimistic Bootstrapping and Backward Induction"

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Rainbow: Combining Improvements in Deep Reinforcement Learning

An educational resource to help anyone learn deep reinforcement learning.

Learning deep representations by mutual information estimation and maximization

A pytorch implementation of MINE(Mutual Information Neural Estimation)

Theano-based implementation of Deep Q-learning

A minimalist environment for decision-making in autonomous driving

The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)

Paper list of multi-agent reinforcement learning (MARL)

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