Complexity of stochastic branch and bound for belief tree search in Bayesian reinforcement learning
Christos Dimitrakakis · UvA-DARE (University of Amsterdam) · 2009
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 lower and stochastic 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 examines the complexity of such algorithms.