Deep Reinforment Learning gallery

Deep reinforcement learning methods implemented in tensorflow2

Requirements

python>=3.7, tensorflow>=2.1, ray>=1.0

DQN (Deep Q Network)

Playing Atari with Deep Reinforcement Learning (2013)

Human-level control through deep reinforcement learning (2015)

OpenAI baselines DQN

Double DQN

Deep Reinforcement Learning with Double Q-learning

Dueling Network

Dueling Network Architectures for Deep Reinforcement Learning

Categorical DQN, C51

A Distributional Perspective on Reinforcement Learning

Prioritized Experience Replay

Prioritized Experience Replay

baselines

Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

QR-DDN

Distributional Reinforcement Learning with Quantile Regression

FQF

Fully Parameterized Quantile Function for Distributional Reinforcement Learning

Ape-X DQN

Distributed Prioritized Experience Replay

R2D2

Recurrent Experience Replay in Distributed Reinforcement Learning

A3C/A2C (Advantage Actor Critic)

Asynchronous Methods for Deep Reinforcement Learning

OpenAI baselines

DDPG

Deterministic Policy Gradient Algorithms

Continuous control with deep reinforcement learning

TD3

Addressing Function Approximation Error in Actor-Critic Methods

TRPO

Trust Region Policy Optimization

PPO

Proximal Policy Optimization Algorithms

SAC

Soft Actor-Critic：Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor、Haarnoja et al、2018

Soft Actor-Critic Algorithms and Applications、Haarnoja et al、2018

Alpha Go Zero / Alpha Zero

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Mastering the game of Go without human knowledge

MuZero

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model