Learning High-Risk High-Precision Motion Control

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

15 Lataukset (Pure)


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.
OtsikkoMIG '22: Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games
ToimittajatStephen N. Spencer
ISBN (elektroninen)978-1-4503-9888-6
DOI - pysyväislinkit
TilaJulkaistu - 3 marrask. 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaACM SIGGRAPH Conference on Motion, Interaction and Games - Guanajuato, Meksiko
Kesto: 3 marrask. 20225 marrask. 2022
Konferenssinumero: 15


ConferenceACM SIGGRAPH Conference on Motion, Interaction and Games
Kaupunki Guanajuato


Sukella tutkimusaiheisiin 'Learning High-Risk High-Precision Motion Control'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä