retro-movies

retro

Retro Games in Gym

atari-reset

Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"

retro-baselines

Publicly releasable baselines for the Retro contest

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

retro-contest

OpenAI Retro Contest

coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

atari-py

A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface

random-network-distillation

Code for the paper "Exploration by Random Network Distillation"

mlsh

Code for the paper "Meta-Learning Shared Hierarchies"

atari-demo

Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"

VLog

Transform Video as a Document with ChatGPT, CLIP, BLIP2, GRIT, Whisper, LangChain.

gym-recording

Add-on package to gym, to record sequences of actions, observations, and rewards

safety-starter-agents

Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Re...

simple-evals

gym-http-api

API to access OpenAI Gym from other languages via HTTP