A library of reinforcement learning components and agents

Benchmark for "Offline Policy Comparison with Confidence"

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Library to Build and Solve Large MDPs.

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

Continual Learning papers list, curated by ContinualAI

CL-Gym: Full-Featured PyTorch Library for Continual Learning

Code for "Dream and Search to Control: Latent Space Planning for Continuous Control"

PyTorch implementation of Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

Pytorch Implementations of Multi Agent Reinforcement Learning(marl) algorithms

OffWorld Gym: Open-Access Physical Robotics Environment for Real-World Reinforcement Learning Benchmark and Research

Seamless copy-and-paste of images with Poisson Blending.

A library for building reinforcement learning and imitation learning agents in Pytorch

The Julia Programming Language

Algorithms for Decision Making textbook

FERM: A Framework for Efficient Robotic Manipulation

Learning n-step actions for control tasks

Source code for the paper "Structured Attention Graphs for Understanding Deep Image Classifications"

Because a well-written code teaches you how to think.

improved Cross Entropy Method for trajectory optimization

[CoRL 2020] Learning a Decentralized Multiarm Motion Planner

Differentiation through cone programs

Generic and specific Gazebo worlds and tools for easily building new ones.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Clean PyTorch implementations of imitation and reward learning algorithms

DexiNed: Dense EXtreme Inception Network for Edge Detection

Exploration map inpainting for frontier selection

This repository contains implementations and illustrative code to accompany DeepMind publications

CartPole env. with continuous action space

Reinforcement learning algorithms for MuJoCo tasks