ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).

Compare two version of an arXiv preprint with a single command.

Tools for running experiments on RL agents in procgen environments

Custom UI for mlflow tracking server

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Massively parallel rigidbody physics simulation on accelerator hardware.

From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

Companion webpage to the book "Mathematics For Machine Learning"

minerl-wrappers compiles common wrappers and standardizes code for reproducibility in the MineRL environment!

The NetHack Learning Environment

Render OpenAI Gym environments in Google Colaboratory

Data analysis for team BeepBoop for MineRL 2020 competition

Benchmarking the Spectrum of Agent Capabilities

Code for the paper "Understanding RL Vision"

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

Rainbow: Combining Improvements in Deep Reinforcement Learning

Stupidly-simple speed measurements for Python.

Starter Kit for the Unity Obstacle Tower challenge

Obstacle Tower Environment

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.