We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is,
algorithms that change its exploration policy as infrequently as possible during regret …

We consider the problem of off-policy evaluation in Markov decision processes. Off-policy
evaluation is the task of evaluating the expected return of one policy with data generated by …

Learning from interaction with the environment–trying untested actions, observing
successes and failures, and tying effects back to causes--is one of the first capabilities we …

This work presents two reinforcement learning (RL) architectures, which mimic rational
humans in the way of analyzing the available information and making decisions. The …

The motivation behind this thesis is to provide efficient solutions for energy harvesting
communications. Firstly, an energy harvesting underlay cognitive radio relaying network is …

The trade-off between exploration and exploitation is a classic problem in rein-forcement
learning that has been the focus of countless research efforts. Informally, the dilemma stems …