CrazySssst

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

sonnet

TensorFlow-based neural network library

tianshou

An elegant PyTorch deep reinforcement learning library.

Deep-Reinforcement-Learning-Algorithms-with-PyTorch

PyTorch implementations of deep reinforcement learning algorithms and environments

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

football

Check out the new game server:

rlpyt

Reinforcement Learning in PyTorch

pymarl

Python Multi-Agent Reinforcement Learning framework

TradeMaster

TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:

softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

awesome-rl-envs

procgen

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

awesome-game-ai

Awesome Game AI materials of Multi-Agent Reinforcement Learning

deep-learning-uncertainty

Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.

minihack

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

atari-representation-learning

Code for "Unsupervised State Representation Learning in Atari"

Awesome-Evolutionary-Reinforcement-Learning

Research Papers and Code Repository on the Integration of Evolutionary Algorithms and Reinforcement Learning

BEAR

Code for Stabilizing Off-Policy RL via Bootstrapping Error Reduction

CDS

[NeurIPS 2021] CDS achieves remarkable success in challenging benchmarks SMAC and GRF by balancing sharing and diversity.

DeepTrader

RE3

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

adversarially-motivated-intrinsic-goals

This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".

lirpg

rapid

[ICLR 2021] Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments.

adversarially-guided-actor-critic

AGAC: Adversarially Guided Actor-Critic

DvD_ES

Code from the paper "Effective Diversity in Population Based Reinforcement Learning", presented as a spotlight at NeurIPS 2020. This is the Evolution Strategies implementation, but of course the method can be used for gradient based RL algorithms (e.g. TD3).

EMC

The code for paper, "Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration", NeurIPS 2021.

mepol

Implementation of the MEPOL algorithm - A policy gradient method for task-agnostic exploration

Anti-exploration-RL

Anti exploration in offline reinforcement learning

dual-policy-distillation