Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...
: Based on the setting of exchangeable bets, this paper proposes a subjectivist view of numerical possibility theory. It relies on the assumption that when an agent constructs a pr...
Representing agent policies compactly is essential for improving the scalability of multi-agent planning algorithms. In this paper, we focus on developing a pruning technique that...
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
Partially Observable Markov Decision Processes (POMDPs) provide an appropriately rich model for agents operating under partial knowledge of the environment. Since finding an opti...
Yan Virin, Guy Shani, Solomon Eyal Shimony, Ronen ...