English
Related papers

Related papers: Sign-Separated Finite-Time Error Analysis of Q-Lea…

200 papers

In recent work it is shown that Q-learning with linear function approximation is stable, in the sense of bounded parameter estimates, under the $(\varepsilon,\kappa)$-tamed Gibbs policy; $\kappa$ is inverse temperature, and $\varepsilon>0$…

Machine Learning · Computer Science 2026-02-09 Prashant Mehta , Sean Meyn

It is well-known that information loss can occur in the classic and simple Q-learning algorithm. Entropy-based policy search methods were introduced to replace Q-learning and to design algorithms that are more robust against information…

Machine Learning · Computer Science 2020-06-29 Tung D. Nguyen , Kathryn E. Kasmarik , Hussein A. Abbass

While reinforcement learning (RL) promises to revolutionize the control of complex nonlinear robotic systems, a profound gap persists between the heuristic success of model-free off-policy deep RL and the underlying theory, which remains…

Machine Learning · Computer Science 2026-05-08 Manuel Haussmann , Mustafa Mert Çelikok , Melih Kandemir

Q-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by…

Machine Learning · Computer Science 2021-04-21 Oren Peer , Chen Tessler , Nadav Merlis , Ron Meir

The objective in this paper is to obtain fast converging reinforcement learning algorithms to approximate solutions to the problem of discounted cost optimal stopping in an irreducible, uniformly ergodic Markov chain, evolving on a compact…

Systems and Control · Computer Science 2019-10-01 Shuhang Chen , Adithya M. Devraj , Ana Bušić , Sean P. Meyn

Q-value iteration (Q-VI) is usually analyzed through the \(\gamma\)-contraction of the Bellman operator. This argument proves convergence to \(Q^*\), but it gives only a coarse account of when the induced greedy policy becomes optimal. We…

Optimization and Control · Mathematics 2026-05-06 Donghwan Lee

Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency. We revisit test-time behavior and uncover a simple yet…

Computation and Language · Computer Science 2026-01-13 Zhen Yang , Mingyang Zhang , Feng Chen , Ganggui Ding , Liang Hou , Xin Tao , Ying-Cong Chen

In offline reinforcement learning (RL), single-step temporal-difference (TD) learning can suffer from bootstrapping error accumulation over long horizons. Action-chunked TD methods mitigate this by backing up over multiple steps, but can…

Machine Learning · Computer Science 2026-03-17 Gwanwoo Song , Kwanyoung Park , Youngwoon Lee

Active learning of finite automata has been vigorously pursued for the purposes of analysis and explanation of black-box systems. In this paper, we study an L*-style learning algorithm for weighted automata over the max-plus semiring. The…

Formal Languages and Automata Theory · Computer Science 2024-07-16 Takamasa Okudono , Masaki Waga , Taro Sekiyama , Ichiro Hasuo

The paper presents a methodology for temporal logic verification of continuous-time switched stochastic systems. Our goal is to find the lower bound on the probability that a complex temporal property is satisfied over a finite time…

Logic in Computer Science · Computer Science 2021-09-28 Mahathi Anand , Pushpak Jagtap , Majid Zamani

In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics. The…

Systems and Control · Electrical Eng. & Systems 2021-05-20 Lei Guo , Han Zhao

A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the termination condition roughly determines its length. Generally, learning with longer options (like…

Artificial Intelligence · Computer Science 2017-12-05 Anna Harutyunyan , Peter Vrancx , Pierre-Luc Bacon , Doina Precup , Ann Nowe

As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for aligning large language models (LLMs) under tight budgets.…

Computation and Language · Computer Science 2026-02-04 Shaobo Wang , Jiaming Wang , Jiajun Zhang , Cong Wang , Yue Min , Zichen Wen , Xingzhang Ren , Fei Huang , Huiqiang Jiang , Junyang Lin , Dayiheng Liu , Linfeng Zhang

The subspace identification method (SIM) has become a widely adopted approach for the identification of discrete-time linear time-invariant (LTI) systems. In this paper, we derive finite sample high-probability error bounds for the system…

Systems and Control · Electrical Eng. & Systems 2025-07-03 Shuai Sun , Weikang Hu , Xu Wang

We propose a robust Q-learning algorithm for Markov decision processes under model uncertainty when each state-action pair is associated with a finite ambiguity set of candidate transition kernels. This finite-measure framework enables…

Optimization and Control · Mathematics 2026-02-10 Julian Sester , Cécile Decker

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when predicting the TD…

Machine Learning · Computer Science 2021-10-29 Litian Liang , Yaosheng Xu , Stephen McAleer , Dailin Hu , Alexander Ihler , Pieter Abbeel , Roy Fox

Traditional approaches to inference of deterministic finite-state automata (DFA) stem from symbolic AI, including both active learning methods (e.g., Angluin's L* algorithm and its variants) and passive techniques (e.g., Biermann and…

Formal Languages and Automata Theory · Computer Science 2025-10-21 Elaheh Hosseinkhani , Martin Leucker

Greedy-GQ with linear function approximation, originally proposed in \cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with the…

Machine Learning · Computer Science 2024-05-03 Yue Wang , Yi Zhou , Shaofeng Zou

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

This brief aims at the issue of globally composite-learning-based neural fast finite-time (F-FnT) tracking control for a class of uncertain systems in strict-feedback form subject to nonlinearly periodic disturbances. First, uncertain…

Systems and Control · Electrical Eng. & Systems 2023-09-22 Xidong Wang , Zhan Li , Zhen He