Our paper “DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards” has been accepted at IJCAI 2023 (w/ @swan_104 @yujin_tang @alanyttian). DEIR explores more efficiently, especially in partially observable tasks. Check out https://arxiv.org/abs/2304.10770 for details, and https://github.com/swan-utokyo/deir for the source code. Tech for Good As the first author, Shanchuan Wan explained his research in Tech for Good (CNN). https://twitter.com/klustout/status/1689324782490198036
Updated as of academic year 2022.
Updated as of academic year 2021.
Zhu Hanhua recieved Excellent Paper Award for his presentation in IEEE TAAI, 2019.
Heterogeneous Multi-Task Learning of Evaluation Functions for Chess and Shogi written by Shanchuan Wan was awarded as a best student paper finalist in ICONIP 2018.
Takahisa Imagawa received Merit Paper Award for his presentation in IEEE Technologies and Applications of Artificial Intelligence 2017.