Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

End-to-end Generative Optimization for AI Agents

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Embodied and organized multi-LLM-agent teams supporting communication for >3 agents. Source codes for the paper "Embodied LLM Agents Learn to Cooperate in Organized Teams".

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

🔥 Datasets and env wrappers for offline safe reinforcement learning

An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.

A PyTorch implementation of Implicit Q-Learning

Repository to accompany RSS 2018 paper on dexterous hand manipulation

A collection of MuJoCo based environments.

Reinforcement learning algorithms for MuJoCo tasks

A benchmark for offline reinforcement learning.

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

An open source robotics benchmark for meta- and multi-task reinforcement learning

robomimic: A Modular Framework for Robot Learning from Demonstration

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull reque…

A toolkit for reproducible reinforcement learning research.

Code for conservative Q-learning

A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning libr…

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…