Hana Hoshino — accepted AI-conference papers

2023

Joint Metrics Matter: A Better Standard for Trajectory Forecasting

Erica Weng, Hana Hoshino, Deva Ramanan, Kris Kitani

ICCV 2023poster

Multi-modal trajectory forecasting methods commonly evaluate using single-agent metrics (marginal metrics), such as minimum Average Displacement Error (ADE) and Final Displacement Error (FDE), which fail to capture joint performance of multiple interacting agents. Only focusing on marginal metrics c…

Cited by 13 PDF ↗code ↗Scholar ↗

2022

OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching

Hana Hoshino, Kei Ota, Asako Kanezaki, Rio Yokota

ICRA 2022poster

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and optimal performance. This limits IRL applications in the real worl…

Cited by 20 Source ↗code ↗Scholar ↗