Abstract— We consider the problem of apprenticeship learning when the expert’s demonstration covers only a small part of a large state space. Inverse Reinforcement Learning (IR...
: The generic problem of estimation and inference given a sequence of i.i.d. samples has been extensively studied in the statistics, property testing, and learning communities. A n...
Probabilistic I/O automata (PIOA) constitute a model for distributed or concurrent systems that incorporates a notion of probabilistic choice. The PIOA model provides a notion of ...
Particle filters are used extensively for tracking the state of non-linear dynamic systems. This paper presents a new particle filter that maintains samples in the state space a...
Labelled Markov processes (LMPs) are automata whose transitions are given by probability distributions. In this paper we present a ‘universal’ LMP as the spectrum of a commutat...