We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions. The task for an age...
Most traditional approaches to probabilistic planning in relationally specified MDPs rely on grounding the problem w.r.t. specific domain instantiations, thereby incurring a com...
Abstract Partially observable Markov decision processes (POMDPs) are a principled mathematical framework for planning under uncertainty, a crucial capability for reliable operation...
Hanna Kurniawati, Yanzhu Du, David Hsu, Wee Sun Le...
Often one has a preference order among the different systems that satisfy a given specification. Under a probabilistic assumption about the possible inputs, such a preference order...
Krishnendu Chatterjee, Thomas A. Henzinger, Barbar...
Abstract— Real-world robotic environments are highly structured. The scalability of planning and reasoning methods to cope with complex problems in such environments crucially de...