Sepideh Nahali, Hajer Ayadi, Jimmy X. Huang, Esmat Pakizeh, Mir Mohsen Pedram, Leila Safari. A Dynamic and Task-Independent Reward Shaping Approach for Discrete Partially Observable Markov Decision Processes. In Hisashi Kashima, Tsuyoshi Idé, Wen-Chih Peng, editors, Advances in Knowledge Discovery and Data Mining - 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2023, Osaka, Japan, May 25-28, 2023, Proceedings, Part II. Volume 13936 of Lecture Notes in Computer Science, pages 337-348, Springer, 2023. [doi]
Abstract is missing.