In this section
@inproceedings{Soh:2011:10.1145/2001576.2001674,
author = {Soh, H and Demiris, Y},
doi = {10.1145/2001576.2001674},
pages = {713--720},
publisher = {ACM},
title = {Evolving Policies for Multi-Reward Partially Observable Markov Decision Processes (MR-POMDPs)},
url = {http://dx.doi.org/10.1145/2001576.2001674},
year = {2011}
}
TY - CPAPER
AB - Plans and decisions in many real-world scenarios are made under uncertainty and to satisfy multiple, possibly conflicting, objectives. In this work, we contribute the multi-reward partially-observable Markov decision process (MR-POMDP) as a general modelling framework. To solve MR-POMDPs, we present two hybrid (memetic) multi-objective evolutionary algorithms that generate non-dominated sets of policies (in the form of stochastic finite state controllers). Performance comparisons between the methods on multi-objective problems in robotics (with 2, 3 and 5 objectives), web-advertising (with 3, 4 and 5 objectives) and infectious disease control (with 3 objectives), revealed that memetic variants outperformed their original counterparts. We anticipate that the MR-POMDP along with multi-objective evolutionary solvers will prove useful in a variety of theoretical and real-world applications.
AU - Soh,H
AU - Demiris,Y
DO - 10.1145/2001576.2001674
EP - 720
PB - ACM
PY - 2011///
SP - 713
TI - Evolving Policies for Multi-Reward Partially Observable Markov Decision Processes (MR-POMDPs)
UR - http://dx.doi.org/10.1145/2001576.2001674
UR - http://hdl.handle.net/10044/1/20001
ER -
