Markov Models
Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning
We design efficient distance approximation algorithms for several classes of well-studied structured high-dimensional distributions.
BayesianRiskMarkovDecisionProcesses
Markov decision process (MDP) is a paradigm for modeling sequential decision making under uncertainty. From a modeling perspective, some parameters of MDPs are unknown and need to be estimated from data. In this paper, we consider MDPs where transition probability and cost parametersarenotknown.
Reinforcement Learningwith State Observation Costsin Action-Contingent Noiselessly Observable Markov Decision Processes
Letb0 be twopositiveObservwill of V(b0) V (b0) after =O(ln (SAH /)), with 1 .
Multi-agentactiveperceptionwithpredictionrewards
Active perception,collecting observations to reduce uncertainty about ahidden variable, isone of the fundamental capabilities of an intelligent agent [2]. In multi-agent active perceptiona team of autonomous agents cooperatively gathers observations to infer the value of a hidden variable.
