A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual...
We present discrete stochastic mathematical models for the growth curves of synchronous and asynchronous evolutionary algorithms with populations structured according to a random ...
Mario Giacobini, Marco Tomassini, Andrea Tettamanz...
Partially Observable Markov Decision Processes (POMDPs) provide an appropriately rich model for agents operating under partial knowledge of the environment. Since finding an opti...
Yan Virin, Guy Shani, Solomon Eyal Shimony, Ronen ...
Abstract. An optimal probabilistic-planning algorithm solves a problem, usually modeled by a Markov decision process, by finding its optimal policy. In this paper, we study the k ...