Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning

Open Access
Authors
  • C. Dimitrakakis
Publication date 2010
Host editors
  • J. Filipe
  • A. Fred
  • B. Sharp
Book title ICAART 2010
Book subtitle proceedings of the 2nd International Conference on Agents and Artificial Intelligence: Valencia, Spain, January 22-24, 2010
ISBN
  • 9789896740214
Event 2nd international conference on agents and artificial intelligence (ICAART 2010), Valencia, Spain
Pages (from-to) 259-264
Publisher Setúbal: INSTICC Press
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most problems of interest, the optimal solution involves planning in an infinitely large tree. However, it is possible to obtain stochastic lower and upper bounds on the value of each tree node. This enables us to use stochastic branch and bound algorithms to search the tree efficiently. This paper proposes some algorithms and examines their complexity in this setting.
Document type Conference contribution
Language English
Published at
https://doi.org/10.5220/0002721402590264 (Final published version)
Downloads
309340.pdf (Accepted author manuscript)
Permalink to this page
Back