Option discovery in reinforcement learning using frequent common subsequences of actions

Date

2005-11-30

Author

Girgin, Sertan
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

5
views

0
downloads

Cite This

Temporally abstract actions, or options, facilitate learning in large and complex domains by exploiting sub-tasks and hierarchical structure of the problem formed by these sub-tasks. In this paper, we study automatic generation of options using common sub-sequences derived from the state transition histories collected as learning progresses. The standard Q-learning algorithm is extended to use generated options transparently, and effectiveness of the method is demostrated in Dietterich's Taxi domain.

URI

https://hdl.handle.net/11511/55280

Collections

Department of Computer Engineering, Conference / Seminar