101 citations · 332 across the 32 of their papers we have counts for
4 papers · 1 filter
A Bilinear Programming Approach for Multiagent Planning
Marek Petrik, Shlomo Zilberstein
Multiagent planning and coordination problems are common and known to be computationally hard. We show that a wide range of two-agent problems can be formulated as bilinear program…
Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation
Marek Petrik, Dharmashankar Subramanian, Janusz Marecki
We propose solution methods for previously-unsolved constrained MDPs in which actions can continuously modify the transition probabilities within some acceptable sets. While many m…
Global Optimization for Value Function Approximation
Marek Petrik, Shlomo Zilberstein
Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bilin…
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes
Marek Petrik, Gavin Taylor, Ron Parr +1
Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions rel…