no code implementations • 11 Mar 2024 • Narim Jeong, Donghwan Lee
We hope that our analysis will deepen the current understanding of soft Q-learning by establishing connections with switching system models and may even pave the way for new frameworks in the finite-time analysis of other reinforcement learning algorithms.
no code implementations • 24 Feb 2024 • Donghwan Lee
This paper analyzes multi-step TD-learning algorithms within the `deadly triad' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping.
no code implementations • 19 Feb 2024 • Han-Dong Lim, HyeAnn Lee, Donghwan Lee
Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches.
no code implementations • 4 Jan 2024 • Donghwan Lee, Do-Wan Kim
The main goal of this paper is to develop a new linear matrix inequality (LMI) condition for the asymptotic stability of continuous-time Takagi-Sugeno (T-S) fuzzy systems.
no code implementations • 11 Oct 2023 • Behrad Moniri, Donghwan Lee, Hamed Hassani, Edgar Dobriban
However, with a constant gradient descent step size, this spike only carries information from the linear component of the target function and therefore learning non-linear components is impossible.
no code implementations • 10 Oct 2023 • HyeAnn Lee, Donghwan Lee
The goal of this paper is to propose a new Q-learning algorithm with a dummy adversarial player, which is called dummy adversarial Q-learning (DAQ), that can effectively regulate the overestimation bias in standard Q-learning.
no code implementations • 1 Oct 2023 • Han-Dong Lim, Donghwan Lee
The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process.
no code implementations • 13 Sep 2023 • Donghwan Lee, Do Wan Kim
Moreover, we establish that the proposed methods offer necessary and sufficient conditions for the local exponential stability of T-S fuzzy systems.
no code implementations • 31 Jul 2023 • Donghwan Lee, Han-Dong Lim, Do Wan Kim
The main goal of this paper is to investigate continuous-time distributed dynamic programming (DP) algorithms for networked multi-agent Markov decision problems (MAMDPs).
no code implementations • 16 Jun 2023 • Han-Dong Lim, Donghwan Lee
Temporal-difference (TD) learning is widely regarded as one of the most popular algorithms in reinforcement learning (RL).
no code implementations • 9 Jun 2023 • Donghwan Lee
The objective of this paper is to investigate the finite-time analysis of a Q-learning algorithm applied to two-player zero-sum Markov games.
no code implementations • 9 Jun 2023 • Xinmeng Huang, Kan Xu, Donghwan Lee, Hamed Hassani, Hamsa Bastani, Edgar Dobriban
MOLAR improves the dependence of the estimation error on the data dimension, compared to independent least squares estimates.
no code implementations • CVPR 2023 • Jaehoon Choi, Dongki Jung, Taejae Lee, SangWook Kim, Youngdong Jung, Dinesh Manocha, Donghwan Lee
We present a new pipeline for acquiring a textured mesh in the wild with a single smartphone which offers access to images, depth maps, and valid poses.
no code implementations • 20 Feb 2023 • Han-Dong Lim, Donghwan Lee
Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications.
1 code implementation • 31 Jan 2023 • Donghwan Lee, Behrad Moniri, Xinmeng Huang, Edgar Dobriban, Hamed Hassani
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain.
no code implementations • 25 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.
no code implementations • 1 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.
1 code implementation • 31 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.
no code implementations • 22 Apr 2022 • Donghwan Lee, Do Wan Kim
TD-learning is a fundamental algorithm in the field of reinforcement learning (RL), that is employed to evaluate a given policy by estimating the corresponding value function for a Markov decision process.
no code implementations • 13 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.
no code implementations • 10 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.
1 code implementation • 3 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.
no code implementations • 11 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.
no code implementations • 29 Dec 2021 • Donghwan Lee, Do Wan Kim
The goal of this manuscript is to conduct a controltheoretic analysis of Temporal Difference (TD) learning algorithms.
no code implementations • 9 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.
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.
no code implementations • CVPR 2021 • Donghwan Lee, Soohyun Ryu, Suyong Yeon, Yonghan Lee, Deokhwa Kim, Cheolho Han, Yohann Cabon, Philippe Weinzaepfel, Nicolas Guérin, Gabriela Csurka, Martin Humenberger
In this paper, we introduce 5 new indoor datasets for visual localization in challenging real-world environments.
no code implementations • 14 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.
no code implementations • 17 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.
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.
no code implementations • 10 Nov 2020 • Jaehoon Choi, Dongki Jung, Yonghan Lee, Deokhwa Kim, Dinesh Manocha, Donghwan Lee
We present a novel algorithm for self-supervised monocular depth completion.
1 code implementation • 6 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.
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.
no code implementations • 4 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.
no code implementations • 1 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 +2
no code implementations • 24 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.
no code implementations • 13 Dec 2018 • Hyung-Jin Yoon, Huaiyu Chen, Kehan Long, Heling Zhang, Aditya Gahlawat, Donghwan Lee, Naira Hovakimyan
The encoding is useful for sharing local visual observations with other agents under communication resource constraints.
no code implementations • 17 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.