By Topic

A novel dynamic priority-based action-selection-mechanism integrating a reinforcement learning

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)
Il Hong Suh ; Graduate Sch. of Inf. & Commun., Hanyang Univ., Seoul, South Korea ; Min Jo Kim ; Sanghoon Lee ; Byung Ju Yi

A novel action-selection-mechanism is proposed to deal with sequential behaviors, where associations between some of stimulus and behaviors would be learned by a shortest-path-finding-based reinforcement learning technique. To be specific, we define behavioral motivation as a primitive node for action selection, and then sequentially construct a network with behavioral motivations. The vertical path of the network represents a behavioral sequence. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, some experimental results on a "pushing-box-into-a-goal (PBIG) task" of a mobile robot is illustrated.

Published in:

Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on  (Volume:3 )

Date of Conference:

26 April-1 May 2004