Prior Preference Learning from Experts:Designing a Reward with Active Inference

no code implementations • 22 Jan 2021 • Jin Young Shin, Cheolhyeong Kim, Hyung Ju Hwang

In this paper, we claim that active inference can be interpreted using reinforcement learning (RL) algorithms and find a theoretical connection between them.

Reinforcement Learning (RL)

Prior Preference Learning From Experts: Designing A Reward with Active Inference

no code implementations • 1 Jan 2021 • Jin Young Shin, Cheolhyeong Kim, Hyung Ju Hwang

In this paper, we claim that active inference can be interpreted using reinforcement learning (RL) algorithms and find a theoretical connection between them.

Reinforcement Learning (RL)

NEAR: Neighborhood Edge AggregatoR for Graph Classification

no code implementations • 6 Sep 2019 • Cheolhyeong Kim, Haeseong Moon, Hyung Ju Hwang

However, past GNN algorithms based on 1-hop neighborhood neural message passing are exposed to a risk of loss of information on local structures and relationships.

General Classification Graph Classification

Local Stability and Performance of Simple Gradient Penalty $\mu$-Wasserstein GAN

no code implementations • ICLR 2019 • Cheolhyeong Kim, Seungtae Park, Hyung Ju Hwang

Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution.

Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN

no code implementations • 5 Oct 2018 • Cheolhyeong Kim, Seungtae Park, Hyung Ju Hwang

Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution.