Temporal difference methods for the variance of the reward to go

Aviv Tamar; Dotan Di Castro; Shie Mannor

Temporal difference methods for the variance of the reward to go

Aviv Tamar, Dotan Di Castro, Shie Mannor

Technion - Israel Institute of Technology

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

Abstract

In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose variants of both TD(0) and LSTD(λ) with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.

Original language	English
Pages (from-to)	1532-1540
Number of pages	9
Journal	Proceedings of Machine Learning Research
Volume	28
State	Published - 2013
Event	30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States Duration: 16 Jun 2013 → 21 Jun 2013

All Science Journal Classification (ASJC) codes

Human-Computer Interaction
Sociology and Political Science

Access to Document

https://proceedings.mlr.press/v28/tamar13.html

Cite this

@article{7fe21af3cd154bb6ae6f0140439af981,

title = "Temporal difference methods for the variance of the reward to go",

abstract = "In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose variants of both TD(0) and LSTD(λ) with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.",

author = "Aviv Tamar and {Di Castro}, Dotan and Shie Mannor",

year = "2013",

language = "الإنجليزيّة",

volume = "28",

pages = "1532--1540",

note = "30th International Conference on Machine Learning, ICML 2013 ; Conference date: 16-06-2013 Through 21-06-2013",

}

TY - JOUR

T1 - Temporal difference methods for the variance of the reward to go

AU - Tamar, Aviv

AU - Di Castro, Dotan

AU - Mannor, Shie

PY - 2013

Y1 - 2013

N2 - In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose variants of both TD(0) and LSTD(λ) with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.

AB - In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance and process control. We propose variants of both TD(0) and LSTD(λ) with linear function approximation, prove their convergence, and demonstrate their utility in a 4-dimensional continuous state space problem.

UR - http://www.scopus.com/inward/record.url?scp=84897478037&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

VL - 28

SP - 1532

EP - 1540

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 30th International Conference on Machine Learning, ICML 2013

Y2 - 16 June 2013 through 21 June 2013

ER -

Temporal difference methods for the variance of the reward to go

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this