A recipe for online RLHF.

Recipes to train reward model for RLHF.

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Imitation learning algorithms

⚡️ Shockingly fast imitation learning algorithms via combining online and offline data engines. ⚡️

The official implementation of Self-Play Fine-Tuning (SPIN)

Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

Contains JAX implementation of algorithms for inverse reinforcement learning

Learning Shared Safety Constraints from Multi-Task Demonstrations (NeurIPS 2023)

Train a language model to answer Slack messages as you.

🚀 A fast safe reinforcement learning library in PyTorch

KwaiRec: A Fully-observed Dataset for Recommender Systems.

Official repo for consistency models.

Code and documentation to train Stanford's Alpaca models, and generate the data.

A modern, high customizable, responsive Jekyll theme for documentation with built-in search.

A C 14-compatible physical units library with no dependencies and a single-file delivery option. Emphasis on safety, accessibility, performance, and developer experience.

An implementation of Deep Q-Learning from Demonstrations (DQfD) for playing Atari 2600 video games

Course materials for Advanced Topics in Statistical Learning, Spring 2023

PyTorch Boilerplate For Research

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

Differentiable Optimization-Based Modeling for Machine Learning

A data-driven, fast driving simulator for multi-agent coordination under partial observability.

L5Kit - https://woven.toyota

Prototyping robots for PyBullet (F1/10 MIT Racecar, Sawyer, Baxter and Dobot arm, Boston Dynamics Atlas and Botlab environment)

Simulator for the INTERACTION dataset