Rens, GFerrein, A2014-02-132014-02-132013-09Rens, G and Ferrein, A. 2013. Belief-node Condensation for Online POMDP Algorithms. In: IEEE AFRICON 2013, Mauritius, 9-12 September 2013http://www.cair.za.net/sites/default/files/outputs/Rens-AFRICON-13.pdfhttp://hdl.handle.net/10204/7190IEEE AFRICON 2013, Mauritius, 9-12 September 2013.We consider online partially observable Markov decision processes (POMDPs) which compute policies by local look-ahead from the current belief-state. One problem is that belief-nodes deeper in the decision-tree increase in the number of states with non-zero probability they contain. Computation time of updating a belief-state is exponential in the number of states contained by the belief. Belief-update occurs for each node in a search tree. It would thus pay to reduce the size of the nodes while keeping the information they contain. In this paper, we compare four fast and frugal methods to reduce the size of belief-nodes in the search tree, hence improving the running-time of online POMDP algorithms.enPartially observable Markov decision processesPOMDPsConference PresentationRens, G., & Ferrein, A. (2013). Belief-node Condensation for Online POMDP Algorithms. Centre for Artificial Intelligence Research. http://hdl.handle.net/10204/7190Rens, G, and A Ferrein. "Belief-node Condensation for Online POMDP Algorithms." (2013): http://hdl.handle.net/10204/7190Rens G, Ferrein A, Belief-node Condensation for Online POMDP Algorithms; Centre for Artificial Intelligence Research; 2013. http://hdl.handle.net/10204/7190 .TY - Conference Presentation AU - Rens, G AU - Ferrein, A AB - We consider online partially observable Markov decision processes (POMDPs) which compute policies by local look-ahead from the current belief-state. One problem is that belief-nodes deeper in the decision-tree increase in the number of states with non-zero probability they contain. Computation time of updating a belief-state is exponential in the number of states contained by the belief. Belief-update occurs for each node in a search tree. It would thus pay to reduce the size of the nodes while keeping the information they contain. In this paper, we compare four fast and frugal methods to reduce the size of belief-nodes in the search tree, hence improving the running-time of online POMDP algorithms. DA - 2013-09 DB - ResearchSpace DP - CSIR KW - Partially observable Markov decision processes KW - POMDPs LK - https://researchspace.csir.co.za PY - 2013 T1 - Belief-node Condensation for Online POMDP Algorithms TI - Belief-node Condensation for Online POMDP Algorithms UR - http://hdl.handle.net/10204/7190 ER -