近年来强化学习分类综述大全，不看后悔，收藏为先！

Evacloud

大纲

强化学习宏观视角

多智能体强化学习

offline rl

off-policy rl

策略估计

逆强化学习

强化学习、模仿学习

分层强化学习

多任务强化学习

adversarial rl

Probabilistic rl

分布式强化学习

Sim-to-Real

奖励塑形

安全强化学习

model-free、model-based强化学习

强化学习状态表示

贝叶斯强化学习

强化学习组合优化

迁移学习强化学习

课程学习强化学习

可解释的强化学习

动态环境强化学习

Human advice强化学习

NLP&rl

强化学习实验

强化学习的应用

1.机器人 2.搜索、推荐、社交 3.经济金融 4.交通运输、能源 5.游戏 6.云计算、物联网 7.自动驾驶、路径规划 8.安全 9.医疗 10.深度学习框架 11.自动控制

其他

正文

强化学习宏观视角

A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions

arxiv.org/abs/2001.0692

A survey of benchmarking frameworks for reinforcement learning

arxiv.org/pdf/2011.1357

Universal Reinforcement Learning Algorithms: Survey and Experiments

arxiv.org/pdf/1705.1055

A Brief Survey of Deep Reinforcement Learning

arxiv.org/pdf/1708.0586

Policy Search in Continuous Action Domains: an Overview

arxiv.org/pdf/1803.0470

A Tour of Reinforcement Learning: The View from Continuous Control

arxiv.org/pdf/1806.0946

多智能体强化学习

An Overview of Multi-agent Reinforcement Learning from Game Theoretical Perspective

arxiv.org/pdf/2011.0058

Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory

arxiv.org/pdf/2001.0648

Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications

arxiv.org/pdf/1812.1179

A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity

arxiv.org/pdf/1707.0918

A Survey and Critique of Multiagent Deep Reinforcement Learning

arxiv.org/pdf/1810.0558

offline rl

Offline (Batch) Reinforcement Learning: A Review of Literature and Applications

Offline (Batch) Reinforcement Learning: A Review of Literature and Applications

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

arxiv.org/pdf/2005.0164

off-policy rl

Off-policy Learning With Eligibility Traces: A Survey

jmlr.org/papers/volume1

策略估计

逆强化学习

A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress

arxiv.org/pdf/1806.0687

强化学习、模仿学习

A Survey of Deep RL and IL for Autonomous Driving Policy Learning

arxiv.org/pdf/2101.0199

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation

arxiv.org/pdf/1612.0713

分层强化学习

Hierarchical principles of embodied reinforcement learning: A review

arxiv.org/pdf/2012.1014

多任务强化学习

A Survey of Multi-Task Deep Reinforcement Learning

mdpi.com/2079-9292/9/9/

adversarial rl

Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning

arxiv.org/pdf/2001.0968

Probabilistic rl

A Short Survey on Probabilistic Reinforcement Learning

arxiv.org/pdf/1901.0701

Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning

arxiv.org/pdf/1908.0938

分布式强化学习

Distributed Deep Reinforcement Learning: An Overview

arxiv.org/pdf/2011.1101

Sim-to-Real

Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

arxiv.org/pdf/2009.1330

奖励塑形

Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

arxiv.org/pdf/2012.0983

A survey on intrinsic motivation in reinforcement learning

arxiv.org/pdf/1908.0697

安全强化学习

Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art

arxiv.org/pdf/2101.0950

model-free、model-based强化学习

Average-reward model-free reinforcement learning: a systematic review and literature mapping

arxiv.org/pdf/2010.0892

Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey

arxiv.org/ftp/arxiv/pap

Model-based Reinforcement Learning: A Survey.

arxiv.org/pdf/2006.1671

Model-Based Deep Reinforcement Learning for High-Dimensional Problems, a Survey

arxiv.org/pdf/2008.0559

A Survey on Applications of Model-Free Strategy Learning in Cognitive Wireless Networks

arxiv.org/pdf/1504.0397

强化学习状态表示

An Overview of Natural Language State Representation for Reinforcement Learning

arxiv.org/pdf/2007.0977

Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations

arxiv.org/pdf/1804.0457

贝叶斯强化学习

Bayesian Reinforcement Learning: A Survey

arxiv.org/pdf/1609.0443

强化学习组合优化

Reinforcement Learning for Combinatorial Optimization: A Survey

arxiv.org/pdf/2003.0360

A Survey on Reinforcement Learning for Combinatorial Optimization

arxiv.org/pdf/2008.1224

迁移学习强化学习

Transfer Learning in Deep Reinforcement Learning: A Survey

arxiv.org/pdf/2009.0788

课程学习强化学习

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey

arxiv.org/pdf/2003.0496

Automatic Curriculum Learning For Deep RL: A Short Survey

arxiv.org/pdf/2003.0466

可解释的强化学习

Explainable Reinforcement Learning: A Survey

arxiv.org/pdf/2005.0624

动态环境强化学习

A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments

arxiv.org/pdf/2005.1061

A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity

arxiv.org/pdf/1707.0918

Human advice强化学习

REINFORCEMENT LEARNING WITH HUMAN ADVICE: A SURVEY.

arxiv.org/pdf/2005.1101

NLP&rl

A Survey of Reinforcement Learning Informed by Natural Language

arxiv.org/pdf/1906.0392

强化学习实验

A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots

arxiv.org/pdf/1909.0377

强化学习的应用

1.机器人

Reinforcement Learning Approaches in Social Robotics

arxiv.org/pdf/2009.0968

Emotion in Reinforcement Learning Agents and Robots: A Survey

arxiv.org/pdf/1705.0517

2.搜索、推荐、社交

Reinforcement Learning based Recommender Systems: A Survey

arxiv.org/pdf/2101.0628

Deep Reinforcement Learning for Search, Recommendation, and Online Advertising: A Survey

arxiv.org/pdf/1812.0712

Applications of Deep Reinforcement Learning in Communications and Networking: A Survey

arxiv.org/pdf/1810.0786

Reinforcement Learning Approaches in Social Robotics

arxiv.org/pdf/2009.0968

3.经济金融

Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

arxiv.org/ftp/arxiv/pap

Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey

arxiv.org/ftp/arxiv/pap

4.交通运输、能源

Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey

arxiv.org/pdf/2005.0093

Deep Reinforcement Learning for Smart Building Energy Management: A Survey

https://arxiv.org/pdf/2008.05074.pdfarxiv.org

weixin.qq.com/g/AwYAAO5<br> (二维码自动识别)

满200的话拉您进2群，加我微信 jjnuxjp5x

5.游戏

A Survey of Deep Reinforcement Learning in Video Games

arxiv.org/pdf/1912.1094

6.云计算、物联网

Reinforcement Learning-based Application Autoscaling in the Cloud: A Survey

arxiv.org/pdf/2001.0995

Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges

arxiv.org/pdf/1907.0905

7.自动驾驶、路径规划

Deep Reinforcement Learning for Autonomous Driving: A Survey

arxiv.org/pdf/2002.0044

Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles

arxiv.org/pdf/2001.1123

8.安全

Deep Reinforcement Learning for Cyber Security

arxiv.org/pdf/1906.0579

9.医疗

Deep Reinforcement Learning for Clinical Decision Support: A Brief Survey

arxiv.org/pdf/1907.0947

Reinforcement Learning in Healthcare: A Survey

arxiv.org/pdf/1908.0879

10.深度学习框架

Deep Reinforcement Learning for Sequence-to-Sequence Models

arxiv.org/pdf/1805.0946

11.自动控制

Optimal and Autonomous Control Using Reinforcement Learning: A Survey

par.nsf.gov/servlets/pu

其他

Derivative-Free Reinforcement Learning: A Review

arxiv.org/pdf/2102.0571

A SHORT SURVEY ON MEMORY BASED REINFORCEMENT LEARNING

arxiv.org/pdf/1904.0673