Using relative novelty to identify useful temporal abstractions in reinforcement learning

Özgür Şimşek, Andrew G. Barto

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

133 Citations (SciVal)

Abstract

We present a new method for automatically creating useful temporal abstractions in reinforcement learning. We argue that states that allow the agent to transition to a different region of the state space are useful subgoals, and propose a method for identifying them using the concept of relative novelty. When such a state is identified, a temporally-extended activity (e.g., an option) is generated that takes the agent efficiently to this state. We illustrate the utility of the method in a number of tasks.
Original languageEnglish
Title of host publicationProceedings of the Twenty-first International Conference on Machine Learning (ICML 2004): Banff, Alberta, Canada, July 4-8, 2004
EditorsCarla E. Brodley
PublisherAssociation for Computing Machinery
Volume69
Publication statusPublished - 1 Jan 2004

Publication series

NameACM International Conference Proceeding Series
PublisherACM

Fingerprint

Dive into the research topics of 'Using relative novelty to identify useful temporal abstractions in reinforcement learning'. Together they form a unique fingerprint.

Cite this