Link

Authors

  • Hongming Zhang* - Peking University (zhanghongming[at]pku.edu.cn)
  • Tianyang Yu - Nanchang University

Abstract

In this chapter, we introduce and summarize the taxonomy and categories for reinforcement learning (RL) algorithms. We classify reinforcement learning algorithms from different perspectives, including model-based and model-free methods, value-based and policy-based methods (or combination of the two), Monte Carlo methods and temporal-difference methods, on-policy and off-policy methods. Most reinforcement learning algorithms can be classified under different categories according to the above criteria, hope this helps to provide the readers some overviews of the full picture before introducing the algorithms in detail in later chapters.

Keywords: model-based, model-free, value-based, policy-based, Monte Carlo (MC) methods, temporal-difference (TD) methods, on-policy, off-policy

Citation

To cite this book, please use this bibtex entry:

@incollection{deepRL-chapter3-2020,
 title={Taxonomy of Reinforcement Learning},
 chapter={3},
 author={Hongming Zhang, Tianyang Yu},
 editor={Hao Dong, Zihan Ding, Shanghang Zhang},
 booktitle={Deep Reinforcement Learning: Fundamentals, Research, and Applications},
 publisher={Springer Nature},
 pages={125-134},
 note={\url{http://www.deepreinforcementlearningbook.org}},
 year={2020}
}

If you find any typos or have suggestions for improving the book, do not hesitate to contact with the corresponding author (name with *).