93 citations · 225 across the 20 of their papers we have counts for
20 papers
Relaxed Conditions for Parameterized Linear Matrix Inequality in the Form of Nested Fuzzy Summations
Do Wan Kim, Donghwan Lee
The aim of this study is to investigate less conservative conditions for parameterized linear matrix inequalities (PLMIs) that are formulated as nested fuzzy summations. Such PLMIs…
Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes
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). In our st…
Finite-Time Analysis of Minimax Q-Learning for Two-Player Zero-Sum Markov Games: Switching System Approach
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. Specifically, we establish a finite-ti…
Finite-Time Analysis of Temporal Difference Learning with Experience Replay
Han-Dong Lim, Donghwan Lee
Temporal-difference (TD) learning is widely regarded as one of the most popular algorithms in reinforcement learning (RL). Despite its widespread use, it has only been recently tha…
Backstepping Temporal Difference Learning
Han-Dong Lim, Donghwan Lee
Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-diff…
Block Double-Submission Attack: Block Withholding Can Be Self-Destructive
Suhyeon Lee, Donghwan Lee, Seungjoo Kim
Proof-of-Work (PoW) is a Sybil control mechanism adopted in blockchain-based cryptocurrencies. It prevents the attempt of malicious actors to manipulate distributed ledgers. Bitcoi…
Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View
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. Although r…
Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints
Xinmeng Huang, Donghwan Lee, Edgar Dobriban +1
In modern machine learning, users often have to collaborate to learn the distribution of the data. Communication can be a significant bottleneck. Prior work has studied homogeneous…
Finite-Time Accuracy of Temporal-Difference Learning Under Schur-Stable Recursions
Donghwan Lee, Do Wan Kim
Temporal difference (TD) learning is a cornerstone reinforcement learning (RL) method for policy evaluation, where the goal is to estimate the value function of a Markov decision p…
Control Theoretic Analysis of Temporal Difference Learning
Donghwan Lee, Do Wan Kim
The goal of this manuscript is to conduct a controltheoretic analysis of Temporal Difference (TD) learning algorithms. TD-learning serves as a cornerstone in the realm of reinforce…
Inducing Functions through Reinforcement Learning without Task Specification
Junmo Cho, Dong-Hwan Lee, Young-Gyu Yoon
We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that…
New Versions of Gradient Temporal Difference Learning
Donghwan Lee, Han-Dong Lim, Jihoon Park +1
Sutton, Szepesvári and Maei introduced the first gradient temporal-difference (GTD) learning algorithms compatible with both linear function approximation and off-policy training.…
Simulation Studies on Deep Reinforcement Learning for Building Control with Human Interaction
Donghwan Lee, Niao He, Seungjae Lee +2
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. Inspire…
SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments
Jaehoon Choi, Dongki Jung, Yonghan Lee +3
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and cor…
SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction
Jaehoon Choi, Dongki Jung, Donghwan Lee +1
Self-supervised monocular depth estimation has emerged as a promising method because it does not require groundtruth depth maps during training. As an alternative for the groundtru…
HARMer: Cyber-attacks Automation and Evaluation
Simon Yusuf Enoch, Zhibin Huang, Chun Yong Moon +3
With the increasing growth of cyber-attack incidences, it is important to develop innovative and effective techniques to assess and defend networked systems against cyber attacks.…
Periodic Q-Learning
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
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
Donghwan Lee, Niao He, Parameswaran Kamalaruban +1
This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and coo…
Primal-Dual Distributed Temporal Difference Learning
Donghwan Lee, Jianghai Hu
The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). T…