Challenges for Relational Reinforcement Learning

M. van Otterlo; Kristian Kersting

Challenges for Relational Reinforcement Learning

M. van Otterlo, Kristian Kersting

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

175 Downloads (Pure)

Abstract

We present a perspective and challenges for Relational Reinforcement Learning (RRL). We first survey existing work and distinguish a number of main directions. We then highlight some research problems that are intrinsically involved in abstracting over relational Markov Decision Processes. These are the challenges of RRL. In addition, we describe a number of issues that will be important for further research into RRL. These are the challenges for RRL and deal with newly arising issues because of relational abstraction.

Original language	English
Title of host publication	Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04
Editors	P. Tadepalli, R Givan, K. Driessens
Place of Publication	Corvallis
Publisher	University of Alberta
Pages	74-80
Number of pages	7
Publication status	Published - 8 Jul 2004
Event	Workshop on Relational Reinforcement Learning 2004 - Banff, Canada Duration: 4 Jul 2004 → 8 Jul 2004

Workshop

Workshop	Workshop on Relational Reinforcement Learning 2004
Country/Territory	Canada
City	Banff
Period	4/07/04 → 8/07/04

Keywords

EWI-13095
IR-64887
METIS-221213
HMI-IA: Intelligent Agents

Access to Document

Cite this

@inproceedings{03ec1af1bb9a405198cd0c6454417aba,

title = "Challenges for Relational Reinforcement Learning",

abstract = "We present a perspective and challenges for Relational Reinforcement Learning (RRL). We first survey existing work and distinguish a number of main directions. We then highlight some research problems that are intrinsically involved in abstracting over relational Markov Decision Processes. These are the challenges of RRL. In addition, we describe a number of issues that will be important for further research into RRL. These are the challenges for RRL and deal with newly arising issues because of relational abstraction.",

keywords = "EWI-13095, IR-64887, METIS-221213, HMI-IA: Intelligent Agents",

author = "{van Otterlo}, M. and Kristian Kersting",

note = "Otterlovan318:2004 ; Workshop on Relational Reinforcement Learning 2004 ; Conference date: 04-07-2004 Through 08-07-2004",

year = "2004",

month = jul,

day = "8",

language = "English",

pages = "74--80",

editor = "P. Tadepalli and R Givan and K. Driessens",

booktitle = "Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04",

publisher = "University of Alberta",

address = "Canada",

}

van Otterlo, M & Kersting, K 2004, Challenges for Relational Reinforcement Learning. in P Tadepalli, R Givan & K Driessens (eds), Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04. University of Alberta, Corvallis, pp. 74-80, Workshop on Relational Reinforcement Learning 2004, Banff, Alberta, Canada, 4/07/04. <http://eecs.oregonstate.edu/research/rrl/papers/final/otterlo_kersting_final.pdf>

Challenges for Relational Reinforcement Learning. / van Otterlo, M.; Kersting, Kristian.
Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04. ed. / P. Tadepalli; R Givan; K. Driessens. Corvallis: University of Alberta, 2004. p. 74-80.

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

TY - GEN

T1 - Challenges for Relational Reinforcement Learning

AU - van Otterlo, M.

AU - Kersting, Kristian

N1 - Otterlovan318:2004

PY - 2004/7/8

Y1 - 2004/7/8

N2 - We present a perspective and challenges for Relational Reinforcement Learning (RRL). We first survey existing work and distinguish a number of main directions. We then highlight some research problems that are intrinsically involved in abstracting over relational Markov Decision Processes. These are the challenges of RRL. In addition, we describe a number of issues that will be important for further research into RRL. These are the challenges for RRL and deal with newly arising issues because of relational abstraction.

AB - We present a perspective and challenges for Relational Reinforcement Learning (RRL). We first survey existing work and distinguish a number of main directions. We then highlight some research problems that are intrinsically involved in abstracting over relational Markov Decision Processes. These are the challenges of RRL. In addition, we describe a number of issues that will be important for further research into RRL. These are the challenges for RRL and deal with newly arising issues because of relational abstraction.

KW - EWI-13095

KW - IR-64887

KW - METIS-221213

KW - HMI-IA: Intelligent Agents

M3 - Conference contribution

SP - 74

EP - 80

BT - Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04

A2 - Tadepalli, P.

A2 - Givan, R

A2 - Driessens, K.

PB - University of Alberta

CY - Corvallis

T2 - Workshop on Relational Reinforcement Learning 2004

Y2 - 4 July 2004 through 8 July 2004

ER -

Challenges for Relational Reinforcement Learning

Abstract

Workshop

Keywords

Access to Document

Fingerprint

Cite this