 Forward and Backward Bellman equations improve the efficiency of EM
algorithm for DEC-POMDPEntropy (Entropy), 2021 |
 Program Synthesis Guided Reinforcement Learning for Partially Observed
EnvironmentsNeural Information Processing Systems (NeurIPS), 2021 |
 Active Inference or Control as Inference? A Unifying ViewInternational Workshop on Affective Interactions (AI), 2020 |
 Learning Hybrid Object Kinematics for Efficient Hierarchical Planning
Under UncertaintyIEEE/RJS International Conference on Intelligent RObots and Systems (IROS), 2019 |
 New inference strategies for solving Markov Decision Processes using
reversible jump MCMCConference on Uncertainty in Artificial Intelligence (UAI), 2009 |
 Anytime Planning for Decentralized POMDPs using Expectation MaximizationConference on Uncertainty in Artificial Intelligence (UAI), 2010 |
