Automatic construction of Markov decision process models for multi-agent reinforcement learning

Darrell L. Young; Chris Eccles

doi:10.1117/12.2557823

21 April 2020 Automatic construction of Markov decision process models for multi-agent reinforcement learning

Darrell L. Young, Chris Eccles

Proceedings Volume 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II; 114130Y (2020) https://doi.org/10.1117/12.2557823
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

This paper describes our current multi-agent reinforcement learning concepts to complement or replace classic operational planning techniques. A neural planner is used to generate many possible paths. Training of the neural planner is a onetime task using a physics-based model to create the training data. The outputs of the neural planner are achievable paths. The path intersections are represented as decision waypoint nodes in a graph. The graph is interpreted as a Markov Decision Process (MDP). The resulting MDP is much faster than non-discretized spaces to train multi-agent reinforcement algorithms because only high-level decision waypoints are considered. The technique is applicable to multiple domains including air, space, land, sea, and cyber-physical domains.

Citation Download Citation

Darrell L. Young and Chris Eccles "Automatic construction of Markov decision process models for multi-agent reinforcement learning", Proc. SPIE 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II, 114130Y (21 April 2020); https://doi.org/10.1117/12.2557823

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