paper-with-me

Papers

Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach

2024-03-11 · Narim Jeong, Donghwan Lee

Soft Q-learning is a variation of Q-learning designed to solve entropy regularized Markov decision problems where an agent aims to maximize the entropy regularized value function. Despite its empirical success, there have been limited theoretical studies of soft Q-learning to date. This paper aims to offer a novel and unified finite-time, control-theoretic analysis of soft Q-learning algorithms. We focus on two types of soft Q-learning algorithms: one utilizing the log-sum-exp operator and the other employing the Boltzmann operator. By using dynamical switching system models, we derive novel finite-time error bounds for both soft Q-learning algorithms. 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.

📄 PDF Abstract BibTeX arXiv:2403.06366

Code (0)

등록된 구현이 없습니다.

Tasks

Q-Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Final Iteration Convergence Bound of Q-Learning: Switching System Approach

2022-05-11 · Donghwna Lee

Q-learning is known as one of the fundamental reinforcement learning (RL) algorithms. Its convergence has been the focus of extensive research over the past several decades. Recently, a new finitetime error bound and ana…

Q-Learningreinforcement-learningReinforcement Learning (RL)

Finite-sample analysis of identification of switched linear systems with arbitrary or restricted switching

2022-03-18 · Shengling Shi, Othmane Mazhar, Bart De Schutter

For the identification of switched systems with a measured switching signal, this work aims to analyze the effect of switching strategies on the estimation error. The data for identification is assumed to be collected fr…

Adaptive event-triggered robust tracking control of soft robots

2025-06-11 · Renjie Ma, Ziyao Qu, Zhijian Hu, Dong Zhao 외

Soft robots manufactured with flexible materials can be highly compliant and adaptive to their surroundings, which facilitates their application in areas such as dexterous manipulation and environmental exploration. This…

A Discrete-Time Switching System Analysis of Q-learning

2021-02-17 · Donghwan Lee, Jianghai Hu, Niao He

This paper develops a novel control-theoretic framework to analyze the non-asymptotic convergence of Q-learning. We show that the dynamics of asynchronous Q-learning with a constant step-size can be naturally formulated …

Q-Learning

Lyapunov-Certified Direct Switching Theory for Q-Learning

2026-04-21 · Donghwan Lee arxiv

Q-learning is a fundamental algorithmic primitive in reinforcement learning. This paper develops a new framework for analyzing Q-learning from a switching linear system (SLS) viewpoint. In particular, we derive a stochas…

Reinforcement Learning