Action-Space Partitioning for Planning

Natalia H. Gardiol, Leslie Pack Kaelbling

For autonomous artificial decision-makers to solve realistic tasks, they need to deal with searching through large state and action spaces under time pressure. We study the problem of planning in such domains and show how structured representations of the environment's dynamics can help partition the action space into a set of equivalence classes at run time. The partitioned action space is then used to produce a reduced set of actions. This technique speeds up search and can yield significant gains in planning efficiency.

Subjects: 1.11 Planning; 1.11 Planning

Submitted: Apr 24, 2007


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.