Stars
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
Public release for paper Policy Learning with a Language Bottleneck (TMLR 2026, RLC TAFM Spotlight).
Pyrallis is a framework for structured configuration parsing from both cmd and files. Simply define your desired configuration structure as a dataclass and let pyrallis do the rest!
PyTorch code and models for the DINOv2 self-supervised learning method.
Karabiner-Elements is a powerful tool for customizing keyboards on macOS
Development repository for the Triton language and compiler
A data-driven, fast driving simulator for multi-agent coordination under partial observability.
A library for distributed ML training with PyTorch
Implementation of the Off Belief Learning algorithm.
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Massively parallel rigidbody physics simulation on accelerator hardware.
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
Python 3.8+ toolbox for submitting jobs to Slurm
An example bot for the Hanabi Live website written in Python
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The project is a platform of zero learning with a library of games.
Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it
A PyTorch Platform for Distributed RL