A Hybrid PAC Reinforcement Learning Algorithm for Human-Robot Interaction

A Hybrid PAC Reinforcement Learning Algorithm for Human-Robot Interaction

This paper offers a new hybrid probably approximately correct (PAC) reinforcement learning (RL) algorithm for Markov decision processes (MDPs) that intelligently maintains favorable features of both model-based and model-free methodologies. The designed algorithm, referred to as the Dyna-Delayed Q-l...

詳細記述

書誌詳細
主要な著者: Ashkan Zehfroosh, Herbert G. Tanner 
フォーマット: 論文
言語:English
出版事項: Frontiers Media S.A. 2022-03-01
シリーズ:Frontiers in Robotics and AI
主題:
reinforcement learning
probably approximately correct
markov decision process
human-robot interaction
sample complexity
オンライン･アクセス:https://www.frontiersin.org/articles/10.3389/frobt.2022.797213/full

インターネット

https://www.frontiersin.org/articles/10.3389/frobt.2022.797213/full

類似資料