Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning

no code implementations • 2 Jun 2024 • Po-Shao Lin, Jia-Fong Yeh, Yi-Ting Chen, Winston H. Hsu

We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks.

3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction

no code implementations • 2 Dec 2021 • Ching-Yu Tseng, Po-Shao Lin, Yu-Jia Liou, Kuan-Chih Huang, Winston H. Hsu

Shifts Challenge: Robustness and Uncertainty under Real-World Distributional Shift is a competition held by NeurIPS 2021.

motion prediction