Learning High-Risk High-Precision Motion Control

Loading...
Thumbnail Image
Access rights
openAccess
Journal Title
Journal ISSN
Volume Title
Conference article in proceedings
Date
2022-11-03
Major/Subject
Mcode
Degree programme
Language
en
Pages
10
1-10
Series
MIG '22: Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games
Abstract
Deep reinforcement learning (DRL) algorithms for movement control are typically evaluated and benchmarked on sequential decision tasks where imprecise actions may be corrected with later actions, thus allowing high returns with noisy actions. In contrast, we focus on an under-researched class of high-risk, high-precision motion control problems where actions carry irreversible outcomes, driving sharp peaks and ridges to plague the state-action reward landscape. Using computational pool as a representative example of such problems, we propose and evaluate State-Conditioned Shooting (SCOOT), a novel DRL algorithm that builds on advantage-weighted regression (AWR) with three key modifications: 1) Performing policy optimization only using elite samples, allowing the policy to better latch on to the rare high-reward action samples; 2) Utilizing a mixture-of-experts (MoE) policy, to allow switching between reward landscape modes depending on the state; 3) Adding a distance regularization term and a learning curriculum to encourage exploring diverse strategies before adapting to the most advantageous samples. We showcase our features’ performance in learning physically-based billiard shots demonstrating high action precision and discovering multiple shot strategies for a given ball configuration.
Description
Keywords
Other note
Citation
Kim , N H , Kirjonen , M & Hämäläinen , P 2022 , Learning High-Risk High-Precision Motion Control . in S N Spencer (ed.) , MIG '22: Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games . , 9 , ACM , pp. 1-10 , ACM SIGGRAPH Conference on Motion, Interaction and Games , Guanajuato , Mexico , 03/11/2022 . https://doi.org/10.1145/3561975.3562943