Using ilp to improve planning in hierarchical reinforcement learning

Using ilp to improve planning in hierarchical reinforcement learning (2000)

Cached

Download Links

[users.rsise.anu.edu.au]
[www.cse.unsw.edu.au]

Other Repositories/Bibliography

DBLP

by Mark Reid , Malcolm Ryan

Venue:	The Tenth International Conference ILP-2000
Citations:	3 - 1 self

BibTeX

@INPROCEEDINGS{Reid00usingilp,
    author = {Mark Reid and Malcolm Ryan},
    title = {Using ilp to improve planning in hierarchical reinforcement learning},
    booktitle = {The Tenth International Conference ILP-2000},
    year = {2000},
    pages = {174--190},
    publisher = {SpringerVerlag}
}

Bookmark

OpenURL

Abstract

Abstract. Hierarchical reinforcement learning has been proposed as a solution to the problem of scaling up reinforcement learning. The RL-TOPs Hierarchical Reinforcement Learning System is an implementation of this proposal which structures an agent’s sensors and actions into various levels of representation and control. Disparity between levels of representation means actions can be misused by the planning algorithm in the system. This paper reports on how ILP was used to bridge these representation gaps and shows empirically how this improved the system’s performance. Also discussed are some of the problems encountered when using an ILP system in what is inherently a noisy and incremental domain. 1

Citations

2827	Reinforcement Learning: An Introduction - Sutton, Barto - 1998
342	Between MDPS and semi-MDPS: a framework for temporal abstraction in reinforcement learning - Sutton, Precup, et al. - 1999
212	Reinforcement learning with hierarchies of machines - Parr, Russell - 1998
183	Teleo-reactive programs for agent control - Nilsson - 1994
102	The MAXQ method for hierarchical reinforcement learning - Dietterich - 1998
88	Relational reinforcement learning - Dzeroski, Raedt, et al.
85	Autonomous Learning from the Environment - Shen - 1994
49	Learning by experimentation: Incremental refinement of incomplete planning domains - Gil - 1994
43	Relational reinforcement learning - Dˇzeroski, Raedt, et al. - 2001
39	Learning Action Models for Reactive Autonomous Agents - Benson - 1996
28	Trading off simplicity and coverage in incremental concept learning - Iba, Wogulis, et al. - 1988
13	RL-TOPs: an architecture for modularity and re-use in reinforcement learning - Ryan, Pendrith - 1998
12	Trading o simplicity and coverage in incremental concept learning - Iba, Wogulis, et al. - 1988
5	Lime: A system for learning relations - Mccreath, Sharma - 1998
4	Learning to fly: An application of hierarchical reinforcement learning - Ryan, Reid - 2000
2	S.Russell: PAC - learnability of determinate logic programs - Dzeroski - 1992
2	Learning to An application of hierarchical reinforcement learning - Ryan, Reid - 2000
1	Learning by experimentation: Incremental re of incomplete planning domains - Gil - 1994