The following publications are possibly variants of this publication:
- Building Adaptive Dialogue Systems Via Bayes-Adaptive POMDPsShaoWei Png, Joelle Pineau, Brahim Chaib-draa. jstsp, 6(8):917-927, 2012. [doi]
- Bayes-Adaptive POMDPs: A New Perspective on the Explore-Exploit Tradeoff in Partially Observable DomainsJoelle Pineau, Stéphane Ross, Brahim Chaib-draa. isaim 2008: [doi]
- Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPsFinale Doshi, Joelle Pineau, Nicholas Roy. isaim 2008: [doi]
- Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPsFinale Doshi, Joelle Pineau, Nicholas Roy. icml 2008: 256-263 [doi]
- Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPsFinale Doshi-Velez, Joelle Pineau, Nicholas Roy. ai, 187:115-132, 2012. [doi]