Task Understanding from Confusing Multi-task Data

no code implementations • ICML 2020 • Xin Su, Yizhou Jiang, Shangqi Guo, Feng Chen

Beyond machine learning's success in the specific tasks, research for learning multiple tasks simultaneously is referred to as multi-task learning.

Multi-Task Learning

Transfering Hierarchical Structure with Dual Meta Imitation Learning

no code implementations • 28 Jan 2022 • Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation Learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations.

Few-Shot Imitation Learning Imitation Learning +1

Transferring Hierarchical Structure with Dual Meta Imitation Learning

no code implementations • 29 Sep 2021 • Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations.

Few-Shot Imitation Learning Imitation Learning +1

Subjective Learning for Open-Ended Data

no code implementations • 27 Aug 2021 • Tianren Zhang, Yizhou Jiang, Xin Su, Shangqi Guo, Feng Chen

In this paper, we present a novel supervised learning framework of learning from open-ended data, which is modeled as data implicitly sampled from multiple domains with the data in each domain obeying a domain-specific target function.