DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jongmin | ko |
dc.contributor.author | Kim, Geon-Hyeong | ko |
dc.contributor.author | Poupart, Pascal | ko |
dc.contributor.author | Kim, Kee-Eung | ko |
dc.date.accessioned | 2019-03-19T01:38:52Z | - |
dc.date.available | 2019-03-19T01:38:52Z | - |
dc.date.created | 2019-03-09 | - |
dc.date.created | 2019-03-09 | - |
dc.date.created | 2019-03-09 | - |
dc.date.issued | 2018-12-06 | - |
dc.identifier.citation | 32nd Conference on Neural Information Processing Systems (NIPS 2018) | - |
dc.identifier.uri | http://hdl.handle.net/10203/251740 | - |
dc.description.abstract | Monte-Carlo Tree Search (MCTS) has been successfully applied to very large POMDPs, a standard model for stochastic sequential decision-making problems. However, many real-world problems inherently have multiple goals, where multiobjective formulations are more natural. The constrained POMDP (CPOMDP) is such a model that maximizes the reward while constraining the cost, extending the standard POMDP model. To date, solution methods for CPOMDPs assume an explicit model of the environment, and thus are hardly applicable to large-scale realworld problems. In this paper, we present CC-POMCP (Cost-Constrained POMCP), an online MCTS algorithm for large CPOMDPs that leverages the optimization of LP-induced parameters and only requires a black-box simulator of the environment. In the experiments, we demonstrate that CC-POMCP converges to the optimal stochastic action selection in CPOMDP and pushes the state-of-the-art by being able to scale to very large problems. | - |
dc.language | English | - |
dc.publisher | Neural Information Processing Systems | - |
dc.title | Monte-Carlo Tree Search for Constrained POMDPs | - |
dc.type | Conference | - |
dc.identifier.wosid | 000461852002047 | - |
dc.identifier.scopusid | 2-s2.0-85064820556 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 32nd Conference on Neural Information Processing Systems (NIPS 2018) | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Montreal Convention Centre | - |
dc.contributor.localauthor | Kim, Kee-Eung | - |
dc.contributor.nonIdAuthor | Lee, Jongmin | - |
dc.contributor.nonIdAuthor | Kim, Geon-Hyeong | - |
dc.contributor.nonIdAuthor | Poupart, Pascal | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.