Direct Soft-Policy Sampling via Langevin Dynamics

Prior-Guided Diffusion Planning for Offline Reinforcement Learning

Actor-Critic without Actor

NeurIPS 2024 DACER

[ICML2025] Official implementation of Efficient Online Reinforcement Learning for Diffusion Policies appearing in ICML 2025.

Official implementation for DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

Modification of DPPO diffusion policies to allow for selecting the initial noise, as required by DSRL

Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training (CVPR 2025)

Official implementation of Diffusion Policy Policy Optimization, arxiv 2024

Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

A collection of reference environments for offline reinforcement learning

Official PyTorch implementation of AlberDICE