Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting th...
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...