Markov Decision Process Framework for Control-Based Reinforcement Learning-Reference-Cited by-同舟云学术

Markov Decision Process Framework for Control-Based Reinforcement Learning

Published:2023-09-28 Issue:2 Volume:51 Page:39-41
ISSN:0163-5999
Container-title:ACM SIGMETRICS Performance Evaluation Review
language:en
Short-container-title:SIGMETRICS Perform. Eval. Rev.

Author:

Lu Yingdong¹,Squillante Mark S.¹,Wah Wu Chai¹

Affiliation:

1. IBM Research, Yorktown Heights, NY, USA

Abstract

For many years, reinforcement learning (RL) has proven to be very successful in solving a wide variety of learning and decision making under uncertainty (DMuU) problems, including those related to game playing and robotic control. Many different RL approaches, with varying levels of success, have been developed to address these problems.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Software

Link

https://dl.acm.org/doi/pdf/10.1145/3626570.3626585

Reference5 articles.

1. On the theory of policy gradient methods: Optimality, approximation, and distribution shift;Agarwal A.;JMLR,2021

2. Canonical piecewise-linear approximations

3. Y. Lu , M.S. Squillante , C.W. Wu . Markov Decision Process Framework for Control-Based Reinforcement Learning . Preprint , May 2023 . Y. Lu, M.S. Squillante, C.W. Wu. Markov Decision Process Framework for Control-Based Reinforcement Learning. Preprint, May 2023.

4. A. Nagabandi , Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. arXiv:1708.02596v2 , 2017 . A. Nagabandi, et al. Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. arXiv:1708.02596v2, 2017.

5. Nonlinear optimal feedback control for lunar module soft landing