Hiroshi Kajino
Papers
1
Total Citations
4
H-Index
1
About
Hiroshi Kajino is a leading researcher in safe reinforcement learning and robotics, with a focus on developing algorithms that enable autonomous agents to explore uncertain environments without compromising safety. His most-cited work, "Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process" (2018), addresses a critical challenge in real-world applications such as planetary exploration and robot navigation—where safety constraints evolve over time. By integrating spatio-temporal Gaussian processes into Markov decision processes, Kajino introduced a framework that guarantees safe exploration even under dynamic conditions, moving beyond static safety assumptions common in prior work. This contribution has laid foundational groundwork for risk-aware decision-making in robotics and AI, earning recognition for its practical relevance in high-stakes domains. Kajino’s research bridges theoretical rigor and applied safety, making him a key figure in advancing trustworthy autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1