"Reward Shaping with Dynamic Trajectory Aggregation."

Takato Okudo, Seiji Yamada (2021)

Details and statistics

DOI: 10.1109/IJCNN52387.2021.9533401

access: closed

type: Conference or Workshop Paper

metadata version: 2021-09-29

a service of  Schloss Dagstuhl - Leibniz Center for Informatics