GENERATING EFFECTIVE INITIATION SETS FOR SUBGOAL-DRIVEN OPTIONS

Date

2019-03-01

Author

DEMİR, ALPER
Cilden, Erkin
Polat, Faruk

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

35
views

0
downloads

Options framework is one of the prominent models serving as a basis to improve learning speed by means of temporal abstractions. An option is mainly composed of three elements: initiation set, option's local policy and termination condition. Although various attempts exist that focus on how to derive high-quality termination conditions for a given problem, the impact of initiation set generation is relatively unexplored. In this work, we propose an effective goal-oriented heuristic method to derive useful initiation set elements via an analysis of the recent history of events. Effectiveness of the method is experimented on various benchmark problems, and the results are discussed.

Subject Keywords

Control and Systems Engineering

URI

https://hdl.handle.net/11511/43531

Journal

ADVANCES IN COMPLEX SYSTEMS

DOI

https://doi.org/10.1142/s0219525919500012

Collections

Department of Computer Engineering, Article

Citation Formats

A. DEMİR, E. Cilden, and F. Polat, “GENERATING EFFECTIVE INITIATION SETS FOR SUBGOAL-DRIVEN OPTIONS,” ADVANCES IN COMPLEX SYSTEMS, vol. 22, no. 2, pp. 0–0, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43531.