Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
EDBT 2026 Demo / reviewers in the wild / expert

Jeongsoo Ha

dblp:23/10202 · also Jeong Soo Ha · DBLP profile ↗
← Back
2ranked-venue papers
1as first author
2since 2021 · last 2023
0000-0001-7963-0571ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 1 first-author · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 1 first-author · 2 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
Representation and self-supervised learning · 46% Reinforcement learning · 30% Transfer learning and domain adaptation · 16%

Topics — the 6 heaviest of 8, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Representation and self-supervised learning
contrastive learning		 0.712023
Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions · AAAI 2023
Machine learning › Representation and self-supervised learning › contrastive learning › multi-view contrastive learning
dual contrastive learning		 0.712023
Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions · AAAI 2023
Machine learning › Reinforcement learning
model-based reinforcement learning		 0.712023
Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions · AAAI 2023
Machine learning › Transfer learning and domain adaptation
zero-shot transfer		 0.712023
Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions · AAAI 2023
Machine learning › Reinforcement learning › deep reinforcement learning
visual reinforcement learning		 0.612022
Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning · IJCAI 2022
Robotics › Motion planning and robot control › robot control › sensor-based control
vision-based control		 0.422023
Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions · AAAI 2023
Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning · IJCAI 2022

Methods — techniques the papers use, named apart from their topics

data augmentation · 1.2world model · 0.7inverse dynamics model · 0.7contrastive learning · 0.7self-supervised learning · 0.6
YearPublicationVenuePosition
2023 Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions
abstract
Model-based reinforcement learning (MBRL) has been used to efficiently solve vision-based control tasks in high-dimensional image observations. Although recent MBRL algorithms perform well in trained observations, they fail when faced with visual distractions in observations. These task-irrelevant distractions (e.g., clouds, shadows, and light) may be constantly present in real-world scenarios. In this study, we propose a novel self-supervised method, Dream to Generalize (Dr. G), for zero-shot MBRL. Dr. G trains its encoder and world model with dual contrastive learning which efficiently captures task-relevant features among multi-view data augmentations. We also introduce a recurrent state inverse dynamics model that helps the world model to better understand the temporal structure. The proposed methods can enhance the robustness of the world model against visual distractions. To evaluate the generalization performance, we first train Dr. G on simple backgrounds and then test it on complex natural video backgrounds in the DeepMind Control suite, and the randomizing environments in Robosuite. Dr. G yields a performance improvement of 117% and 14% over prior works, respectively. Our code is open-sourced and available at https://github.com/JeongsooHa/DrG.git
Jeongsoo Ha, Yusung Kim 0001
 AAAI1
2022 Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning
abstract
Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more important if those distractions are not exposed during training. We design a Self-Predictive Dynamics (SPD) method to extract task-relevant features efficiently, even in unseen observations after training. SPD uses weak and strong augmentations in parallel, and learns representations by predicting inverse and forward transitions across the two-way augmented versions. In a set of MuJoCo visual control tasks and an autonomous driving task (CARLA), SPD outperforms previous studies in complex observations, and significantly improves the generalization performance for unseen observations. Our code is available at https://github.com/unigary/SPD.
Jeongsoo Ha, Yusung Kim 0001
 IJCAI2