Sciweavers

Share
ICAART
2010
INSTICC

Complexity of Stochastic Branch and Bound Methods for Belief Tree Search in Bayesian Reinforcement Learning

9 years 10 months ago
Complexity of Stochastic Branch and Bound Methods for Belief Tree Search in Bayesian Reinforcement Learning
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 two such algorithms and examines their complexity in this setting.
Christos Dimitrakakis
AttachmentsSize
icaart.pdf316.85 KB
Added 11 Mar 2010
Updated 07 Apr 2010
Type Conference
Year 2010
Where ICAART
Authors Christos Dimitrakakis
Attachments 1 file(s)
Comments (0)
books