Feedback Capacity of Ising Channels With Large Alphabet via Reinforcement Learning-Reference-Cited by-同舟云学术

Feedback Capacity of Ising Channels With Large Alphabet via Reinforcement Learning

Author:

Aharoni Ziv¹^ORCID,Sabag Oron²^ORCID,Permuter Haim H.³^ORCID

Affiliation:

1. Department of Electrical Engineering, Ben-Gurion University of the Negev, Be’er Sheva, Israel

2. Department of Electrical and Computer Engineering, California Institute of Technology, Pasadena, CA, USA

3. Department of Computer Engineering, Ben-Gurion University of the Negev, Be’er Sheva, Israel

Funder

German Research Foundation (DFG) via the German–Israeli Project Cooperation

Israeli Science Foundation

Israeli Innovation Authority as part of the Worldwide Innovative Networking (WIN) Consortium

Israeli Scholarship Education Foundation (ISEF) International Postdoctoral Fellowship

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Library and Information Sciences,Computer Science Applications,Information Systems

Link

Reference41 articles.

1. Gradient estimation using stochastic computation graphs;schulman;Proc Adv Neural Inf Process Syst,2015

2. Prioritized experience replay;schaul;arXiv 1511 05952,2015

5. PILCO: A model-based and dataefficient approach to policy search;deisenroth;Proc 28th Int Conf Mach Learn (ICML),2011

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献