activity
20152023
most citedReinforcement Learning Evaluation and Solution for the Feedback Capacity of the Ising Channel with Large Alphabet

5 citations · 7 across the 6 of their papers we have counts for

collaborators

7 papers

math.OC2021

Reducing the LQG Cost with Minimal Communication

Oron Sabag, Peida Tian, Victoria Kostina +1

We study the linear quadratic Gaussian (LQG) control problem, in which the controller's observation of the system state is such that a desired cost is unattainable. To achieve the…

cs.IT20205 cited

Reinforcement Learning Evaluation and Solution for the Feedback Capacity of the Ising Channel with Large Alphabet

Ziv Aharoni, Oron Sabag, Haim Henri Permuter

We propose a new method to compute the feedback capacity of unifilar finite state channels (FSCs) with memory using reinforcement learning (RL). The feedback capacity was previousl…

cs.IT2020

Computing the Feedback Capacity of Finite State Channels using Reinforcement Learning

Ziv Aharoni, Oron Sabag, Haim Henry Permuter

In this paper, we propose a novel method to compute the feedback capacity of channels with memory using reinforcement learning (RL). In RL, one seeks to maximize cumulative rewards…

cs.IT2019

Graph-Based Encoders and their Performance for Finite-State Channels with Feedback

Oron Sabag, Bashar Huleihel, Haim Permuter

The capacity of unifilar finite-state channels in the presence of feedback is investigated. We derive a new evaluation method to extract graph-based encoders with their achievable…

cs.IT2017

Feedback Capacity and Coding for the -RLL Input-Constrained BEC

Ori Peled, Oron Sabag, Haim H. Permuter

The input-constrained binary erasure channel (BEC) with strictly causal feedback is studied. The channel input sequence must satisfy the -runlength limited (RLL) constraint,…

cs.IT2016

A Single-Letter Upper Bound on the Feedback Capacity of Unifilar Finite-State Channels

Oron Sabag, Haim H. Permuter, Henry D. Pfister

An upper bound on the feedback capacity of unifilar finite-state channels (FSCs) is derived. A new technique, called the -contexts, is based on a construction of a directed grap…