English
Related papers

Related papers: Regularized Q-learning through Robust Averaging

200 papers

We introduce the lookahead-bounded Q-learning (LBQL) algorithm, a new, provably convergent variant of Q-learning that seeks to improve the performance of standard Q-learning in stochastic environments through the use of ``lookahead'' upper…

Machine Learning · Computer Science 2020-06-30 Ibrahim El Shar , Daniel R. Jiang

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Machine Learning · Computer Science 2022-02-22 Ming-Chang Chiu , Xuezhe Ma

We establish optimal Statistical Query (SQ) lower bounds for robustly learning certain families of discrete high-dimensional distributions. In particular, we show that no efficient SQ algorithm with access to an $\epsilon$-corrupted binary…

Data Structures and Algorithms · Computer Science 2022-06-10 Ilias Diakonikolas , Daniel M. Kane , Yuxin Sun

Linear regression is a data analysis technique, which is categorized as supervised learning. By utilizing known data, we can predict unknown data. Recently, researchers have explored the use of quantum annealing (QA) to perform linear…

Quantum Physics · Physics 2024-10-14 Asuka Koura , Takashi Imoto , Katsuki Ura , Yuichiro Matsuzaki

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the…

Optimization and Control · Mathematics 2025-07-21 Narim Jeong , Donghwan Lee , Niao He

Dynamic treatment regimes (DTRs) formalize medical decision-making as a sequence of rules for different stages, mapping patient-level information to recommended treatments. In practice, estimating an optimal DTR using observational data…

Methodology · Statistics 2024-12-11 Jian Sun , Bo Fu , Li Su

Multi-agent reinforcement learning (MARL) has witnessed a remarkable surge in interest, fueled by the empirical success achieved in applications of single-agent reinforcement learning (RL). In this study, we consider a distributed…

Artificial Intelligence · Computer Science 2025-07-30 Han-Dong Lim , Donghwan Lee

We propose a non-convex training objective for robust binary classification of data sets in which label noise is present. The design is guided by the intention of solving the resulting problem by adiabatic quantum optimization. Two…

Quantum Physics · Physics 2012-05-31 Vasil S. Denchev , Nan Ding , S. V. N. Vishwanathan , Hartmut Neven

We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability metrics, such as the…

Machine Learning · Computer Science 2022-02-22 Jia-Jie Zhu , Christina Kouridi , Yassine Nemmour , Bernhard Schölkopf

Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias…

Machine Learning · Computer Science 2018-02-01 Roy Fox , Ari Pakman , Naftali Tishby

Unmanned Aerial Vehicles need an online path planning capability to move in high-risk missions in unknown and complex environments to complete them safely. However, many algorithms reported in the literature may not return reliable…

This paper proposes a novel robust reinforcement learning framework for discrete-time linear systems with model mismatch that may arise from the sim-to-real gap. A key strategy is to invoke advanced techniques from control theory. Using the…

Systems and Control · Electrical Eng. & Systems 2023-12-07 Leilei Cui , Tamer Başar , Zhong-Ping Jiang

In this paper, we investigate a special class of quadratic-constrained quadratic programming (QCQP) with semi-definite constraints. Traditionally, since such a problem is non-convex and N-hard, the neural network (NN) is regarded as a…

Machine Learning · Computer Science 2024-07-10 Xiucheng Wang , Qi Qiu , Nan Cheng

Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped Double Q-learning, as an effective variant of Double Q-learning, employs the clipped double estimator to approximate the…

Machine Learning · Computer Science 2021-05-04 Haobo Jiang , Jin Xie , Jian Yang

We leverage the duality between risk-averse and distributionally robust optimization (DRO) to devise a distributionally robust estimator that strictly outperforms the empirical average for all probability distributions with negative excess…

Statistics Theory · Mathematics 2024-06-21 Nikolas Koumpis , Dionysis Kalogerias

Equalizer parameter optimization is critical for signal integrity in high-speed memory systems operating at multi-gigabit data rates. However, existing methods suffer from computationally expensive eye diagram evaluation, optimization of…

Machine Learning · Computer Science 2026-05-07 Muhammad Usama , Dong Eui Chang

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 as a discrete-time…

Optimization and Control · Mathematics 2024-08-23 Donghwan Lee , Jianghai Hu , Niao He

We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our…

Machine Learning · Statistics 2018-05-14 Ruidi Chen , Ioannis Ch. Paschalidis

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

Machine Learning · Statistics 2019-06-17 Elena Smirnova , Elvis Dohmatob , Jérémie Mary

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency…

Machine Learning · Computer Science 2026-02-17 Yuhang Li , Reena Elangovan , Xin Dong , Priyadarshini Panda , Brucek Khailany