Search Results for author: Seung-Woo Seo

Found 6 papers, 1 papers with code

Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning

no code implementations ICML 2020 Sang-Hyun Lee, Seung-Woo Seo

To address this challenge, previous imitation learning methods exploit task-specific knowledge, e. g., labeling demonstrations manually or specifying termination conditions for each sub-task.

Imitation Learning Self-Supervised Learning

Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning

no code implementations19 Jun 2022 Se-Wook Yoo, Seung-Woo Seo

Our proposed method derives the variational lower bound of the situational mutual information to optimize it.

Imitation Learning Multi-Task Learning +2

GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving

1 code implementation3 Jun 2022 Se-Wook Yoo, Chan Kim, Jin-Woo Choi, Seong-Woo Kim, Seung-Woo Seo

Applying reinforcement learning to autonomous driving entails particular challenges, primarily due to dynamically changing traffic flows.

Autonomous Driving motion prediction +1

Learning Neural Processes on the Fly

no code implementations29 Sep 2021 Younghwa Jung, Zhenyuan Yuan, Seung-Woo Seo, Minghui Zhu, Seong-Woo Kim

In this paper, we propose a new algorithm called anytime neural processes that combines DNNs and SNNs and can work in both low-data and high-data regimes.


RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

no code implementations3 May 2021 Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung-Ju Hwang, Jinwoo Shin

Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning.

Contrastive Learning

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