Okudo, Takato, Yamada, Seiji (2021). Subgoal-Based Reward Shaping to Improve Efficiency in Reinforcement Learning. IEEE Access.
Okudo, Takato, Yamada, Seiji (2021). Subgoal-Based Reward Shaping to Improve Efficiency in Reinforcement Learning. IEEE Access, 9, pp. 97557–97568. doi:10.1109/access.2021.3090364