The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

The NetHack Learning Environment

The official Meta Llama 3 GitHub site

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

A unified evaluation framework for large language models

Set of tools to assess and improve LLM security.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…

Awesome Open-ended AI

Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023) 足球游戏智能体

Unified Reinforcement Learning Framework

Official implementation of HARL algorithms based on PyTorch.

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

StarCraft II Learning Environment

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

A playbook for systematically maximizing the performance of deep learning models.

Check out the new game server:

Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".

A tool for aggregating and plotting MARL experiment data.

SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning

Accelerated Quality-Diversity

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Nethack Learning Environment Wrapper for Language Interface

The release codes of LA-MCTS with its application to Neural Architecture Search.

Scaling scaling laws with board games.

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set …

Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.

Simple editor for making minihack DES files.