Many reinforcement learning (RL) tasks, especially in robotics, consist of multiple sub-tasks that are strongly structured. Such task structures can be exploited by incorporating hierarchical policies that consist of gating networks and sub-policies. However, this concept has only been partially explored for real world settings and complete methods, derived from first principles, are needed. Re...

We present an analytical formula for the asymptotic relative entropy of entanglement with respect to positive partial transpose states for Werner states of arbitrary dimension. We then demonstrate its validity using methods from convex optimization. This is the first case in which the asymptotic value of a subadditive entanglement measure has been calculated.

Some logarithmic trace inequalities involving the notions of relative entropy are reobtained from a log-majorization result. The thermodynamic inequality is generalized and a chain of equivalent statements involving this inequality and the Peierls-Bogoliubov inequality is obtained.

We consider the problem of imitation learning where the examples, demonstrated by an expert, cover only a small part of a large state space. Inverse Reinforcement Learning (IRL) provides an efficient tool for generalizing the demonstration, based on the assumption that the expert is optimally acting in a Markov Decision Process (MDP). Most of the past work on IRL requires that a (near)optimal p...

Anonymity is the property of maintaining secret the identity of users performing a certain action. Anonymity protocols often use random mechanisms which can be described probabilistically. In this paper, we propose a probabilistic process calculus to describe protocols for ensuring anonymity, and we use the notion of relative entropy from information theory to measure the degree of anonymity th...

Many thermodynamic relations involve inequalities, with equality if a process does not involve dissipation. In this article we provide equalities in which the dissipative contribution is shown to involve the relative entropy (also called the Kullback-Leibler divergence). The processes considered are general time evolutions in both classical and quantum mechanics, and the initial state is someti...

Given an irreducible subshift of finite type X , a subshift Y , a factor map π : X → Y , and an ergodic invariant measure ν on Y , there can exist more than one ergodic measure on X which projects to ν and has maximal entropy among all measures in the fiber, but there is an explicit bound on the number of such maximal entropy preimages.

We review the properties of the quantum relative entropy function and discuss its application to problems of classical and quantum information transfer and to quantum data compression. We then outline further uses of relative entropy to quantify quantum entanglement and analyze its manipulation. 1 Quantum relative entropy In this paper we discuss several uses of the quantum relative entropy fun...