Title :
Approximate planning in POMDPs via MDP heuristic
Author :
Yong Lin ; Xingjia Lu ; Makedon, Fillia
Author_Institution :
Coll. of Sci., Ningbo Univ. of Technol., Ningbo, China
Abstract :
MDP heuristic based POMDP algorithms have been considered as simple, fast, but imprecise solutions. This paper provides a novel MDP heuristic value iteration algorithm for POMDPs. Besides the help of MDP, our algorithm utilizes a weighted graph model for the belief point approximation and reassignment, to further improve the efficiency and decrease the space complexity. Experimental results indicate our algorithm is fast and has high solution quality for POMDP problems.
Keywords :
Markov processes; approximation theory; computational complexity; graph theory; iterative methods; planning (artificial intelligence); MDP heuristic value iteration algorithm; POMDP; approximate planning; belief point approximation; belief point reassignment; partially observable Markov decision process; space complexity; weighted graph model; Approximation algorithms; Approximation methods; Convergence; Heuristic algorithms; Mathematical model; Planning; Trajectory;
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
DOI :
10.1109/IJCNN.2014.6889576
