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...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Ashkan Zehfroosh, Herbert G. Tanner 
Materialtyp: Artikel
Språk:English
Publicerad: Frontiers Media S.A. 2022-03-01
Serie:Frontiers in Robotics and AI
Ämnen:
reinforcement learning
probably approximately correct
markov decision process
human-robot interaction
sample complexity
Länkar:https://www.frontiersin.org/articles/10.3389/frobt.2022.797213/full

Internet

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

Liknande verk