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

Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.

Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

Official implementation for "PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning" (NeurIPS 2024)

This is the official code for the paper "Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming" (ICML 2024).

NeurIPS'24 Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning

Self supervised reward function + Phasic Policy Gradient

Unsupervised RL & Maximum Entropy RL: the DIAYN algorithm

TwinHead-RL is a research project on curiosity-driven deep RL. We use a multi-head agent that learns both policy and future state prediction, using prediction error as a dynamic intrinsic reward for efficient exploration and representation learning.

This repository contains an updated implementation of the DIAYN algorithm compatible with newer versions of MuJoCo and OpenAI Gym

The public repository for our ICML'23 paper CLUTR: Curriculum Learning via Unsupervised Task Representation Learning