Model-based Bayesian Reinforcement Learning in Partially Observable Domains


Bayesian reinforcement learning in partially observable domains is notoriously difficult, in part due to the unknown form of the beliefs and the optimal value function. We show that beliefs represented by mixtures of products of Dirichlet distributions are closed under belief updates for factored domains. Belief monitoring algorithms that use this mixture… (More)


2 Figures and Tables


Citations per Year

79 Citations

Semantic Scholar estimates that this publication has 79 citations based on the available data.

See our FAQ for additional information.