What good are actions? Accelerating learning using learned action priors

Benjamin Rosman, Subramanian Ramamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The computational complexity of learning in sequential decision problems grows exponentially with the number of actions available to the agent at each state. We present a method for accelerating this process by learning action priors that express the usefulness of each action in each state. These are learned from a set of different optimal policies from many tasks in the same state space, and are used to bias exploration away from less useful actions. This is shown to improve performance for tasks in the same domain but with different goals. We extend our method to base action priors on perceptual cues rather than absolute states, allowing the transfer of these priors between tasks with differing state spaces and transition functions, and demonstrate experimentally the advantages of learning with action priors in a reinforcement learning context.
Original languageEnglish
Title of host publicationDevelopment and Learning and Epigenetic Robotics (ICDL), 2012 IEEE International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
ISBN (Print)978-1-4673-4964-2
DOIs
Publication statusPublished - 2012

Fingerprint

Dive into the research topics of 'What good are actions? Accelerating learning using learned action priors'. Together they form a unique fingerprint.

Cite this