CVAE-based Far-sighted Intention Inference for Opponent Modeling in Multi-agent Reinforcement Learning

Most interactive environments are non-stationary for agents, as the behaviors of their opponents continually change, which can impair the performance of reinforcement learning algorithms. This impairment can be alleviated by modeling opponents to predict their future movements. To predict more preci...

Celý popis

Podrobná bibliografia

Vydané v:	Chinese Control Conference s. 5847 - 5851
Hlavní autori:	Pei, Yu, Xu, XiaoPeng, Liu, Zhong, Wang, Kuo, Zhu, Li, Wang, Dong
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	Technical Committee on Control Theory, Chinese Association of Automation 28.07.2024
Predmet:	Analytical models Attention mechanisms conditional variational autoencoder (CVAE) Decision making Games intention inference Multi-agent reinforcement learning opponent modeling Prediction algorithms Predictive models Reinforcement learning
ISSN:	1934-1768
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!