Inverse Reinforcement Learning based on Critical State

DOI

10.2991/ifsa-eusflat-15.2015.109How to use a DOI?

Keywords

Inverse Reinforcement learning, reward function, reward feature.

Abstract

Inverse reinforcement learning is tried to search a reward function based on Markov Decision Process. In the IRL topics, experts produce some good traces to make agents learn and adjust the reward function. But the function is difficult to set in some complicate problems. In this paper, Inverse Reinforcement Learning based on Critical State (IRLCS) is proposed to search a succinct and meaningful reward function. IRLCS select a set of reward indexes from whole state space through comparing the difference between the good and bad demonstrations. According to the simulation results, IRLCS can search a good strategy that is similar to experts.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kao-Shing Hwang
AU  - Tien-Yu Cheng
AU  - Wei-Cheng Jiang
PY  - 2015/06
DA  - 2015/06
TI  - Inverse Reinforcement Learning based on Critical State
BT  - Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology
PB  - Atlantis Press
SP  - 771
EP  - 775
SN  - 1951-6851
UR  - https://doi.org/10.2991/ifsa-eusflat-15.2015.109
DO  - 10.2991/ifsa-eusflat-15.2015.109
ID  - Hwang2015/06
ER  -