The Fast Cross-Platform Package Manager

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

Decentralized LLM decision-making for multi-agent path finding on POGEMA

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A conda-forge distribution.

Python Multi-Agent Reinforcement Learning framework

A Tiny biped duck robot 🦆

Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching

Q-learning with Adjoint Matching

A benchmark for offline goal-conditioned RL and offline RL

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

[NeurIPS 2026] Sparse Video Generation Model for Embodied Navigation conditioned on loose language guidance, 100% real world verification

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

[CoRL 2025] ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Denoising Diffusion Implicit Models

Denoising Diffusion Probabilistic Models

Soft Actor-Critic

Simplifying diffusion/flow policies by treating action trajectories as flow trajectories

The official implementation of flow Q-learning (FQL)

Code for conservative Q-learning

Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

An educational resource to help anyone learn deep reinforcement learning.

This repository contains implementations and illustrative code to accompany DeepMind publications

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

A collection of reference environments for offline reinforcement learning

An Open Source Machine Learning Framework for Everyone