We present a technique for computing approximately optimal solutions to stochastic resource allocation problems modeled as Markov decision processes (MDPs). We exploit two key pro...
Nicolas Meuleau, Milos Hauskrecht, Kee-Eung Kim, L...
There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of m...
Raphen Becker, Shlomo Zilberstein, Victor R. Lesse...
Partially observable Markov decision processes (POMDPs) allow one to model complex dynamic decision or control problems that include both action outcome uncertainty and imperfect ...
Agents often have to construct plans that obey deadlines or, more generally, resource limits for real-valued resources whose consumption can only be characterized by probability d...
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...