Regular decision processes: Modelling dynamic systems without using hidden variables

Ronen I. Brafman; Giuseppe De Giacomo

Regular decision processes: Modelling dynamic systems without using hidden variables

Ronen I. Brafman, Giuseppe De Giacomo

Department of Computer Science

Ben-Gurion University of the Negev

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.

Original language	American English
Title of host publication	18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
Pages	1844-1846
Number of pages	3
ISBN (Electronic)	9781510892002
State	Published - 1 Jan 2019
Event	18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 - Montreal, Canada Duration: 13 May 2019 → 17 May 2019 https://dl.acm.org/doi/proceedings/10.5555/3306127

Publication series

Name	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume	3

Conference

Conference	18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
Country/Territory	Canada
City	Montreal
Period	13/05/19 → 17/05/19
Internet address	https://dl.acm.org/doi/proceedings/10.5555/3306127

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Software
Control and Systems Engineering

Cite this

@inproceedings{80fd1f49d5014d42babe6a30e5e99f73,

title = "Regular decision processes: Modelling dynamic systems without using hidden variables",

abstract = "We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.",

author = "Brafman, \{Ronen I.\} and \{De Giacomo\}, Giuseppe",

note = "Publisher Copyright: {\textcopyright} 2019 International Foundation for Autonomous Agents and Multiagent Systems. All rights reserved.; 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 ; Conference date: 13-05-2019 Through 17-05-2019",

year = "2019",

month = jan,

day = "1",

language = "American English",

series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

pages = "1844--1846",

booktitle = "18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019",

url = "https://dl.acm.org/doi/proceedings/10.5555/3306127",

}

Brafman, RI & De Giacomo, G 2019, Regular decision processes: Modelling dynamic systems without using hidden variables. in 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, vol. 3, pp. 1844-1846, 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019, Montreal, Canada, 13/05/19.

Regular decision processes: Modelling dynamic systems without using hidden variables. / Brafman, Ronen I.; De Giacomo, Giuseppe.
18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019. 2019. p. 1844-1846 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Regular decision processes

T2 - 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019

AU - Brafman, Ronen I.

AU - De Giacomo, Giuseppe

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.

AB - We describe Regular Decision Processes (RDPs) a model in between MDPs and POMDPs. Like in POMDPs, the effect of an action may depend on the entire history of actions and observations, but this dependence is restricted to regular functions only. This makes RDP a tractable, yet rich model, that does not hypothesize hidden state, and could possibly be useful for learning dynamic systems.

UR - http://www.scopus.com/inward/record.url?scp=85076917395&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

SP - 1844

EP - 1846

BT - 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019

Y2 - 13 May 2019 through 17 May 2019

ER -

Regular decision processes: Modelling dynamic systems without using hidden variables

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this