Multi-Agent Planning with Baseline Regret Minimization
Keyword(s):
We propose a novel baseline regret minimization algorithm for multi-agent planning problems modeled as finite-horizon decentralized POMDPs. It guarantees to produce a policy that is provably better than or at least equivalent to the baseline policy. We also propose an iterative belief generation algorithm to effectively and efficiently minimize the baseline regret, which only requires necessary iterations to converge to the policy with minimum baseline regret. Experimental results on common benchmark problems confirm its advantage comparing to the state-of-the-art approaches.
Keyword(s):
2019 ◽
Vol 33
◽
pp. 6062-6069
◽
2019 ◽
Vol 33
◽
pp. 4295-4303
◽
2018 ◽
Vol 27
(02)
◽
pp. 1850005
2012 ◽
Vol 542-543
◽
pp. 294-301
Keyword(s):
2014 ◽
Vol 23
(06)
◽
pp. 1460028
◽
Keyword(s):
2012 ◽
Vol 45
◽
pp. 565-600
◽
Keyword(s):
2018 ◽
Vol 21
(62)
◽
pp. 103
◽