This paper introduces a new concept, a decision tree (or list) over tree patterns, which is a natural extension of a decision tree (or decision list), for dealing with tree struct...
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is ...
Niranjan Srinivas, Andreas Krause, Sham Kakade, Ma...
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
Almost every routing protocol in mobile ad hoc networks (MANETs) depends on a broadcast scheme to disseminate routing information. For this reason, creating an efficient broadcast...
Probabilistic planning problems are typically modeled as a Markov Decision Process (MDP). MDPs, while an otherwise expressive model, allow only for sequential, non-durative action...