Recent work has led to the development of an elegant theory of Linearly Solvable Markov Decision Processes (LMDPs) and related Path-Integral Control Problems. Traditionally, LMDPs...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Abstract-- This paper deals with the problems of decentralized implementability and decentralized regular implementability in the context of finite-dimensional linear differential ...
In this paper, we employ an anatomical parameterization of spatial warps to reveal structural differences between medical images of healthy control subjects and disease patients. T...
Background: A major goal of molecular biology is determining the mechanisms that control the transcription of genes. Motif Enrichment Analysis (MEA) seeks to determine which DNA-b...