danijar

handout

Turn Python scripts into handouts with Markdown and figures

dreamerv3

Mastering Diverse Domains through World Models

dreamerv2

Mastering Atari with Discrete World Models

dreamer

Dream to Control: Learning Behaviors by Latent Imagination

crafter

Benchmarking the Spectrum of Agent Capabilities

daydreamer

DayDreamer: World Models for Physical Robot Learning

director

Deep Hierarchical Planning from Pixels

embodied

Fast reinforcement learning research

ninjax

General Modules for JAX

elements

Building blocks for productive research

crafter-baselines

Docker containers of baseline agents for the Crafter environment

diamond_env

Standardized Minecraft Diamond Environment for Reinforcement Learning

zerofun

Remote function calls for array data using ZMQ

dotfiles

My Linux and Mac configuration

npgame

Write simple games in Numpy!

awesome-rl-envs

imptools

Tools for improving Python imports

bridgewalk

Visual reinforcement learning benchmark for controllability

cowherd

Partially-observed visual reinforcement learning domain

definitions

Load and validate YAML definitions against a schema

chunkedfile

Save file writes into multiple chunks

minerl

PPO-RND

Random network distillation on Montezuma's Revenge and Super Mario Bros.

cloudpath

Extend pathlib to GCS, S3, HDFS via TensorFlow's GFile

conny

Recurrent neural network implementation targeted towards evaluating new topologies

danijar

gym

A toolkit for developing and comparing reinforcement learning algorithms.

lab

A customisable 3D platform for agent-based AI research

memory-maze

Memory Maze environment for evaluating long-term memory of RL agents.

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.