Measuring and characterizing generalization in deep reinforcement learning

Measuring and characterizing generalization in deep reinforcement learning

Abstract Deep reinforcement learning (RL) methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports insightful action decisions. We re‐examine what is...

Full description

Bibliographic Details
Main Authors: Sam Witty, Jun K. Lee, Emma Tosch, Akanksha Atrey, Kaleigh Clary, Michael L. Littman, David Jensen
Format: Article
Language:English
Published: Wiley 2021-12-01
Series:Applied AI Letters
Subjects:
deep reinforcement learning
empirical methods
generalization
Q‐networks
Online Access:https://doi.org/10.1002/ail2.45

Internet

https://doi.org/10.1002/ail2.45

Similar Items