Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs.

Finale Doshi Joelle Pineau Nicholas Roy Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs. 256-263 2008 ICML http://doi.acm.org/10.1145/1390156.1390189 conf/icml/2008 db/conf/icml/icml2008.html#DoshiPR08