Seiji Yamada

Online Learning of Shaping Reward with Subgoal Knowledge

2021

SARSA-RS is a reward shaping method that updates the shaping through learning. However, the bottleneck of this method is the aggregation of states since designers need to design mappings from all states to abstract states. …

Balancing Performance and Human Autonomy With Implicit Guidance Agent

2021 · Frontiers in Artificial Intelligence

The human-agent team, which is a problem in which humans and autonomous agents collaborate to achieve one task, is typical in human-AI collaboration. For effective collaboration, humans want to have an effective plan, but in …

Learning Dual-Path Soft Decision Trees for Vision Prototype XAI

2025 · IEEE Access

Following the principle of “this part supports that decision,” prototype-based models achieve visual task reasoning by matching parts to reference patterns. While the explanations are intuitive, they are not locally faithful and fail to quantify …