Search Results for author: Hana Hoshino

Found 2 papers, 2 papers with code

Joint Metrics Matter: A Better Standard for Trajectory Forecasting

1 code implementation • ICCV 2023 • Erica Weng, Hana Hoshino, Deva Ramanan, Kris Kitani

In response to the limitations of marginal metrics, we present the first comprehensive evaluation of state-of-the-art (SOTA) trajectory forecasting methods with respect to multi-agent metrics (joint metrics): JADE, JFDE, and collision rate.

Trajectory Forecasting

Paper
Code

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

1 code implementation • 9 Sep 2021 • Hana Hoshino, Kei Ota, Asako Kanezaki, Rio Yokota

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious.

reinforcement-learning Reinforcement Learning (RL)

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.