Improving the learning rate by inducing a transition model

Robert Bridle; Eric McCreath

Improving the learning rate by inducing a transition model

Robert Bridle^*, Eric McCreath

^*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent. We discuss an approach that incorporates transition model learning within a contemporary agent design.

Original language	English
Title of host publication	Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004
Editors	N.R. Jennings, C. Sierra, L. Sonenberg, M. Tambe
Pages	1330-1331
Number of pages	2
Publication status	Published - 2004
Event	Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004 - New York, NY, United States Duration: 19 Jul 2004 → 23 Jul 2004

Publication series

Name	Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004
Volume	3

Conference

Conference	Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004
Country/Territory	United States
City	New York, NY
Period	19/07/04 → 23/07/04

Cite this

Bridle, R., & McCreath, E. (2004). Improving the learning rate by inducing a transition model. In N. R. Jennings, C. Sierra, L. Sonenberg, & M. Tambe (Eds.), Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004 (pp. 1330-1331). (Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004; Vol. 3).

Bridle, Robert ; McCreath, Eric. / Improving the learning rate by inducing a transition model. Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004. editor / N.R. Jennings ; C. Sierra ; L. Sonenberg ; M. Tambe. 2004. pp. 1330-1331 (Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004).

@inproceedings{14a36435b71647e18ed845c06202aa39,

title = "Improving the learning rate by inducing a transition model",

abstract = "In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent. We discuss an approach that incorporates transition model learning within a contemporary agent design.",

author = "Robert Bridle and Eric McCreath",

year = "2004",

language = "English",

isbn = "1581138644",

series = "Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004",

pages = "1330--1331",

editor = "N.R. Jennings and C. Sierra and L. Sonenberg and M. Tambe",

booktitle = "Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004",

note = "Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004 ; Conference date: 19-07-2004 Through 23-07-2004",

}

Bridle, R & McCreath, E 2004, Improving the learning rate by inducing a transition model. in NR Jennings, C Sierra, L Sonenberg & M Tambe (eds), Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004. Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004, vol. 3, pp. 1330-1331, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004, New York, NY, United States, 19/07/04.

Improving the learning rate by inducing a transition model. / Bridle, Robert; McCreath, Eric.
Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004. ed. / N.R. Jennings; C. Sierra; L. Sonenberg; M. Tambe. 2004. p. 1330-1331 (Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004; Vol. 3).

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

TY - GEN

T1 - Improving the learning rate by inducing a transition model

AU - Bridle, Robert

AU - McCreath, Eric

PY - 2004

Y1 - 2004

N2 - In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent. We discuss an approach that incorporates transition model learning within a contemporary agent design.

AB - In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent. We discuss an approach that incorporates transition model learning within a contemporary agent design.

UR - http://www.scopus.com/inward/record.url?scp=4544281945&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1581138644

SN - 9781581138641

T3 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004

SP - 1330

EP - 1331

BT - Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004

A2 - Jennings, N.R.

A2 - Sierra, C.

A2 - Sonenberg, L.

A2 - Tambe, M.

T2 - Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004

Y2 - 19 July 2004 through 23 July 2004

ER -

Bridle R, McCreath E. Improving the learning rate by inducing a transition model. In Jennings NR, Sierra C, Sonenberg L, Tambe M, editors, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004. 2004. p. 1330-1331. (Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2004).

Improving the learning rate by inducing a transition model

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this