Search Results for author: Donghwan Lee

Found 23 papers, 3 papers with code

Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View

no code implementations25 Jul 2022 Han-Dong Lim, Donghwan Lee

Q-learning has long been one of the most popular reinforcement learning algorithms, and theoretical analysis of Q-learning has been an active research topic for decades.


Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints

no code implementations1 Jun 2022 Xinmeng Huang, Donghwan Lee, Edgar Dobriban, Hamed Hassani

In modern machine learning, users often have to collaborate to learn the distribution of the data.

Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark

1 code implementation31 May 2022 Martin Humenberger, Yohann Cabon, Noé Pion, Philippe Weinzaepfel, Donghwan Lee, Nicolas Guérin, Torsten Sattler, Gabriela Csurka

In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms.

Autonomous Driving Image Retrieval +3

Analysis of Temporal Difference Learning: Linear System Approach

no code implementations22 Apr 2022 Donghwan Lee, Do Wan Kim

In this paper, we propose a simple control theoretic finite-time analysis of TD-learning, which exploits linear system models and standard notions in linear system communities.


A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments

no code implementations13 Mar 2022 Hyungtae Lim, Suyong Yeon, Soohyun Ryu, Yonghan Lee, Youngji Kim, JaeSeong Yun, Euigon Jung, Donghwan Lee, Hyun Myung

As verified in indoor and outdoor 3D LiDAR datasets, our proposed method yields robust global registration performance compared with other global registration methods, even for distant point cloud pairs.

SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning

no code implementations10 Mar 2022 Jaehoon Choi, Dongki Jung, Yonghan Lee, Deokhwa Kim, Dinesh Manocha, Donghwan Lee

Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation.

Monocular Depth Estimation Robot Navigation +2

T-Cal: An optimal test for the calibration of predictive models

1 code implementation3 Mar 2022 Donghwan Lee, Xinmeng Huang, Hamed Hassani, Edgar Dobriban

We find that detecting mis-calibration is only possible when the conditional probabilities of the classes are sufficiently smooth functions of the predictions.

Regularized Q-learning

no code implementations11 Feb 2022 Han-Dong Lim, Do Wan Kim, Donghwan Lee

This paper develops a new Q-learning algorithm that converges when linear function approximation is used.

Q-Learning reinforcement-learning

Control Theoretic Analysis of Temporal Difference Learning

no code implementations29 Dec 2021 Donghwan Lee

The goal of this paper is to investigate a control theoretic analysis of linear stochastic iterative algorithm and temporal difference (TD) learning.


New Versions of Gradient Temporal Difference Learning

no code implementations9 Sep 2021 Donghwan Lee, Han-Dong Lim, Jihoon Park, Okyong Choi

Sutton, Szepesv\'{a}ri and Maei introduced the first gradient temporal-difference (GTD) learning algorithms compatible with both linear function approximation and off-policy training.

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

no code implementations ICCV 2021 Dongki Jung, Jaehoon Choi, Yonghan Lee, Deokhwa Kim, Changick Kim, Dinesh Manocha, Donghwan Lee

We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e. g., a department store or a metro station.

3D Reconstruction Depth Estimation

Simulation Studies on Deep Reinforcement Learning for Building Control with Human Interaction

no code implementations14 Mar 2021 Donghwan Lee, Niao He, Seungjae Lee, Panagiota Karava, Jianghai Hu

The building sector consumes the largest energy in the world, and there have been considerable research interests in energy consumption and comfort management of buildings.

Management reinforcement-learning

A Discrete-Time Switching System Analysis of Q-learning

no code implementations17 Feb 2021 Donghwan Lee, Jianghai Hu, Niao He

Based on these two systems, we derive a new finite-time error bound of asynchronous Q-learning when a constant stepsize is used.


A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms

no code implementations NeurIPS 2020 Donghwan Lee, Niao He

This paper develops a novel and unified framework to analyze the convergence of a large family of Q-learning algorithms from the switching system perspective.


SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction

1 code implementation6 Oct 2020 Jaehoon Choi, Dongki Jung, Donghwan Lee, Changick Kim

In this paper, we propose SAFENet that is designed to leverage semantic information to overcome the limitations of the photometric loss.

Depth Prediction Monocular Depth Estimation +1

Periodic Q-Learning

no code implementations L4DC 2020 Donghwan Lee, Niao He

The use of target networks is a common practice in deep reinforcement learning for stabilizing the training; however, theoretical understanding of this technique is still limited.


A Unified Switching System Perspective and O.D.E. Analysis of Q-Learning Algorithms

no code implementations4 Dec 2019 Donghwan Lee, Niao He

In this paper, we introduce a unified framework for analyzing a large family of Q-learning algorithms, based on switching system perspectives and ODE-based stochastic approximation.


Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents

no code implementations1 Dec 2019 Donghwan Lee, Niao He, Parameswaran Kamalaruban, Volkan Cevher

This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and cooperate.

Distributed Optimization Multi-agent Reinforcement Learning +1

Target-Based Temporal Difference Learning

no code implementations24 Apr 2019 Donghwan Lee, Niao He

The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side.


Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process

no code implementations17 Sep 2018 Hyung-Jin Yoon, Donghwan Lee, Naira Hovakimyan

The objective is to study an on-line Hidden Markov model (HMM) estimation-based Q-learning algorithm for partially observable Markov decision process (POMDP) on finite state and action sets.


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