We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...
In this paper, we discuss the use of Targeted Trajectory Distribution Markov Decision Processes (TTD-MDPs)—a variant of MDPs in which the goal is to realize a specified distrib...
Sooraj Bhat, David L. Roberts, Mark J. Nelson, Cha...
Appearance-based localization compares the current image taken from a robot's camera to a set of pre-recorded images in order to estimate the current location of the robot. S...
The causal states of computational mechanics define the minimal sufficient (prescient) memory for a given stationary stochastic process. They induce the -machine which is a hidden...
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...