Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces. Decisions are based on a Particle Filter for estimating the bel...
Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Marko...
Abstract--The difficulties encountered in sequential decisionmaking problems under uncertainty are often linked to the large size of the state space. Exploiting the structure of th...
—We aim to characterize the maximum link throughput of a multi-channel opportunistic communication system. The states of these channels evolve as independent and identically dist...
—We consider opportunistic communications over multiple channels where the state (“good” or “bad”) of each channel evolves as independent and identically distributed Mark...