English
Related papers

Related papers: Optimistic Training and Convergence of Q-Learning …

200 papers

We show that learning-rate schedules for large model training behave surprisingly similar to a performance bound from non-smooth convex optimization theory. We provide a bound for the constant schedule with linear cooldown; in particular,…

Machine Learning · Computer Science 2025-07-24 Fabian Schaipp , Alexander Hägele , Adrien Taylor , Umut Simsekli , Francis Bach

The goal of this paper is to investigate new and simple convergence analysis of dynamic programming for linear quadratic regulator problem of discrete-time linear time-invariant systems. In particular, bounds on errors are given in terms of…

Optimization and Control · Mathematics 2021-06-18 Donghwan Lee

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…

Machine Learning · Computer Science 2026-04-08 Masoud S. Sakha , Rushikesh Kamalapurkar , Sean Meyn

In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in…

Machine Learning · Computer Science 2024-11-01 Jia Lin Hau , Erick Delage , Esther Derman , Mohammad Ghavamzadeh , Marek Petrik

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

Establishing robust policies is essential to counter attacks or disturbances affecting deep reinforcement learning (DRL) agents. Recent studies explore state-adversarial robustness and suggest the potential lack of an optimal robust policy…

Machine Learning · Computer Science 2024-06-24 Haoran Li , Zicheng Zhang , Wang Luo , Congying Han , Yudong Hu , Tiande Guo , Shichen Liao

Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deployment in real-world domains. In this work, we address the challenge of cross-run policy…

Machine Learning · Computer Science 2026-05-22 Marcel Hussing , Liv G. d'Aliberti , Claas Voelcker , Benjamin Eysenbach , Eric Eaton

The quadratic assignment problem (QAP) is a fundamental NP-hard task that poses significant challenges for both traditional heuristics and modern learning-based solvers. Existing QAP solvers still struggle to achieve consistently…

Machine Learning · Computer Science 2026-04-23 Yicheng Pan , Ruisong Zhou , Haijun Zou , Tianyou Li , Zaiwen Wen

The convergence of many reinforcement learning (RL) algorithms with linear function approximation has been investigated extensively but most proofs assume that these methods converge to a unique solution. In this paper, we provide a…

Machine Learning · Computer Science 2019-05-29 Marcus Hutter , Samuel Yang-Zhao , Sultan J. Majeed

Achieving convergence of multiple learning agents in general $N$-player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their application to autonomous systems. Yet it is known that, outside…

Computer Science and Game Theory · Computer Science 2023-01-24 Aamal Abbas Hussain , Francesco Belardinelli , Georgios Piliouras

The problem of learning threshold functions is a fundamental one in machine learning. Classical learning theory implies sample complexity of $O(\xi^{-1} \log(1/\beta))$ (for generalization error $\xi$ with confidence $1-\beta$). The private…

Machine Learning · Computer Science 2022-11-14 Edith Cohen , Xin Lyu , Jelani Nelson , Tamás Sarlós , Uri Stemmer

We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…

Machine Learning · Computer Science 2026-03-05 Shengbo Wang

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how…

Machine Learning · Computer Science 2024-12-11 Tian Tian , Lin F. Yang , Csaba Szepesvári

We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call "optimistic closure," which is…

Machine Learning · Statistics 2019-12-10 Yining Wang , Ruosong Wang , Simon S. Du , Akshay Krishnamurthy

Risk-averse total-reward Markov Decision Processes (MDPs) offer a promising framework for modeling and solving undiscounted infinite-horizon objectives. Existing model-based algorithms for risk measures like the entropic risk measure (ERM)…

Machine Learning · Computer Science 2025-10-27 Xihong Su , Jia Lin Hau , Gersi Doko , Kishan Panaganti , Marek Petrik

The problem of on-line off-policy evaluation (OPE) has been actively studied in the last decade due to its importance both as a stand-alone problem and as a module in a policy improvement scheme. However, most Temporal Difference (TD) based…

Machine Learning · Statistics 2017-02-24 Assaf Hallak , Shie Mannor

In offline reinforcement learning (RL) we have no opportunity to explore so we must make assumptions that the data is sufficient to guide picking a good policy, taking the form of assuming some coverage, realizability, Bellman completeness,…

Machine Learning · Computer Science 2023-11-14 Masatoshi Uehara , Nathan Kallus , Jason D. Lee , Wen Sun

Physics-informed neural solvers offer a promising route to model-based reinforcement learning in continuous time, where optimal feedback synthesis is governed by Hamilton--Jacobi--Bellman (HJB) equations. Practical implementations often…

Machine Learning · Computer Science 2026-05-11 Minseok Kim , Yeongjong Kim , Namkyeong Cho , Yeoneung Kim

Recent studies claim that human behavior in a two-armed Bernoulli bandit (TABB) task is described by positivity and confirmation biases, implying that humans do not integrate new information objectively. However, we find that even if the…

Artificial Intelligence · Computer Science 2025-05-14 Prakhar Godara