The quintessential model-based reinforcement-learning agent iteratively refines its
estimates or prior beliefs about the true underlying model of the environment. Recent …

A default assumption in the design of reinforcement-learning algorithms is that a decision-
making agent always explores to learn optimal behavior. In sufficiently complex …

We investigate the capacity-achieving symbol distributions for directly modulated laser
(DML) and direct-detection (DD) systems utilizing probabilistic constellation shaped pulse …

Agents that learn to select optimal actions represent a prominent focus of the sequential
decision-making literature. In the face of a complex environment or constraints on time and …

All sequential decision-making agents explore so as to acquire knowledge about a
particular target. It is often the responsibility of the agent designer to construct this target …

The capacity of noisy quantum channels characterizes the highest rate at which information
can be reliably transmitted and it is therefore of practical as well as fundamental importance …

The Blahut-Arimoto algorithm is a well-known method to compute classical channel
capacities and rate-distortion functions. Recent works have extended this algorithm to …

The Arimoto-Blahut algorithm for computing the capacity of a discrete memoryless channel
is revisited. A so-called “squeezing” strategy is used to design algorithms that preserve its …

In this paper, we investigate the convergence speed of the Arimoto-Blahut algorithm. For
many channel matrices, the convergence speed is exponential, but for some channel …

We generalize alternating optimization algorithms of Blahut-Arimoto type to the quantum
setting. In particular, we give iterative algorithms to compute the mutual information of …