Point-Based POMDP Algorithms: Improved Analysis and Implementation
Trey Smith, Reid Simmons
Existing complexity bounds for point-based POMDP value iteration algorithms focus either on the curse of dimensionality or the curse of history. We derive a new bound that relies on both and uses the concept of discounted reachability; our conclusions may help guide future algorithm design. We also discuss recent improvements to our (point-based) heuristic search value iteration algorithm. Our new implementation calculates tighter initial bounds, avoids solving linear programs, and makes more effective use of sparsity.
PDF Link: /papers/05/p542-smith.pdf
AUTHOR = "Trey Smith
and Reid Simmons",
TITLE = "Point-Based POMDP Algorithms: Improved Analysis and Implementation",
BOOKTITLE = "Proceedings of the Twenty-First Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-05)",
PUBLISHER = "AUAI Press",
ADDRESS = "Arlington, Virginia",
YEAR = "2005",
PAGES = "542--549"