Sonic to knuckles: evaluations on transfer reinforcement learning

Nathaniel Hamilton; Lena Schlemmer; Christopher Menart; Chad Waddington; Todd Jenkins; Taylor T. Johnson

doi:10.1117/12.2559546

23 April 2020 Sonic to knuckles: evaluations on transfer reinforcement learning

Nathaniel Hamilton, Lena Schlemmer, Christopher Menart, Chad Waddington, Todd Jenkins, Taylor T. Johnson

Proceedings Volume 11425, Unmanned Systems Technology XXII; 114250J (2020) https://doi.org/10.1117/12.2559546
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

Reinforcement Learning holds the potential to enable many systems with rapid, intelligent automated decision- making. However, reinforcement learning on embodied systems is a much greater challenge than the simulated environments and tasks which have been solved to date. A learner in an embodied system cannot run millions of trials or easily tolerate fatal trajectories. Therefore, the ability to train agents in simulated environments and effectively transfer their knowledge to real-world environments will be crucial, and likely an integral part of constructing future robotic systems. We perform experiments in an original transfer reinforcement learning task we constructed using the game “Sonic 3 and Knuckles," evaluating two transfer learning techniques from the literature.

Conference Presentation

Citation Download Citation

Nathaniel Hamilton, Lena Schlemmer, Christopher Menart, Chad Waddington, Todd Jenkins, and Taylor T. Johnson "Sonic to knuckles: evaluations on transfer reinforcement learning", Proc. SPIE 11425, Unmanned Systems Technology XXII, 114250J (23 April 2020); https://doi.org/10.1117/12.2559546

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available