Unknown mixing times in apprenticeship and reinforcement learning

Tom Zahavy; Alon Cohen; Haim Kaplan; Yishay Mansour

Unknown mixing times in apprenticeship and reinforcement learning

Tom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour

School of Computer Science

Tel Aviv University

Research output: Contribution to journal › Conference article › peer-review

Abstract

We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.

Original language	English
Pages (from-to)	430-439
Number of pages	10
Journal	Proceedings of Machine Learning Research
Volume	124
State	Published - 2020
Event	36th Conference on Uncertainty in Artificial Intelligence, UAI 2020 - Virtual, Online Duration: 3 Aug 2020 → 6 Aug 2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 4 Quality Education

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence
Control and Systems Engineering
Statistics and Probability

Cite this

@article{2a6ae360c6594520815e6ece27b2ca56,

title = "Unknown mixing times in apprenticeship and reinforcement learning",

abstract = "We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.",

author = "Tom Zahavy and Alon Cohen and Haim Kaplan and Yishay Mansour",

note = "Publisher Copyright: {\textcopyright} 2020 Proceedings of Machine Learning Research. All rights reserved.; 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020 ; Conference date: 03-08-2020 Through 06-08-2020",

year = "2020",

language = "الإنجليزيّة",

volume = "124",

pages = "430--439",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Unknown mixing times in apprenticeship and reinforcement learning

AU - Zahavy, Tom

AU - Cohen, Alon

AU - Kaplan, Haim

AU - Mansour, Yishay

PY - 2020

Y1 - 2020

N2 - We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.

AB - We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.

UR - http://www.scopus.com/inward/record.url?scp=85162692697&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 2640-3498

VL - 124

SP - 430

EP - 439

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020

Y2 - 3 August 2020 through 6 August 2020

ER -

Unknown mixing times in apprenticeship and reinforcement learning

Abstract

UN SDGs

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this