cartgr

Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

LLMs-for-Social-Robotics

Code and data for our IROS paper: "Are Large Language Models Aligned with People's Social Intuitions for Human–Robot Interactions?"

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

awesome-rlhf

An index of algorithms for reinforcement learning from human feedback (rlhf))

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

Shimmy

An API conversion tool for popular external reinforcement learning environments

Value-Augmented-Sampling

altar_game

A simple altar game based on Phaser3

genetic-mdp

Maximum diversity problem solver in Python using a genetic algorithm

on-policy

This is the official implementation of Multi-Agent PPO (MAPPO).

DESlib

A Python library for dynamic classifier and ensemble selection

concordia

A library for generative social simulation

neural-mmo

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

awesome-rl-envs

nash-mtl

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

state_of_nature

Harvard Joint CS + Government Thesis Project 2018-2019: Escaping the State of Nature

hanabi-learning-environment

hanabi_learning_environment is a research platform for Hanabi experiments.

ai-safety-gridworlds

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

openrlbenchmark

morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.

choices13k

CENTaUR

PantheonRL

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

awesome-phd-advice

Collection of advice for prospective and current PhD students

Melting-Pot-Contest-2023

marlgrid

Gridworld for MARL experiments

Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

meltingpot

A suite of test scenarios for multi-agent reinforcement learning.