We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
We present a new approximation algorithm based on an exact representation of the state space S, using decision diagrams, and of the transition rate matrix R, using Kronecker algeb...
Andrew S. Miner, Gianfranco Ciardo, Susanna Donate...
We introduce point-based dynamic programming (DP) for decentralized partially observable Markov decision processes (DEC-POMDPs), a new discrete DP algorithm for planning strategie...
We develop an exact dynamic programming algorithm for partially observable stochastic games (POSGs). The algorithm is a synthesis of dynamic programming for partially observable M...
Eric A. Hansen, Daniel S. Bernstein, Shlomo Zilber...
In this paper, a market-based decomposition method for decomposable linear systems is developed. The solution process iterates between a master problem that solves the market-matc...