English
Related papers

Related papers: SQT -- std $Q$-target

200 papers

MinMaxMin $Q$-learning is a novel optimistic Actor-Critic algorithm that addresses the problem of overestimation bias ($Q$-estimations are overestimating the real $Q$-values) inherent in conservative RL algorithms. Its core formula relies…

Machine Learning · Computer Science 2024-06-04 Nitsan Soffair , Shie Mannor

Bias problems in the estimation of $Q$-values are a well-known obstacle that slows down convergence of $Q$-learning and actor-critic methods. One of the reasons of the success of modern RL algorithms is partially a direct or indirect…

Machine Learning · Computer Science 2025-06-26 Leif Döring , Benedikt Wille , Maximilian Birr , Mihail Bîrsan , Martin Slowik

$Q$-learning is one of the most fundamental reinforcement learning (RL) algorithms. Despite its widespread success in various applications, it is prone to overestimation bias in the $Q$-learning update. To address this issue, double…

Machine Learning · Computer Science 2026-01-13 Hyunjun Na , Donghwan Lee

DDPG is hindered by the overestimation bias problem, wherein its $Q$-estimates tend to overstate the actual $Q$-values. Traditional solutions to this bias involve ensemble-based methods, which require significant computational resources, or…

Artificial Intelligence · Computer Science 2024-06-04 Nitsan Soffair , Shie Mannor

Overestimation is a fundamental characteristic of model-free reinforcement learning (MF-RL), arising from the principles of temporal difference learning and the approximation of the Q-function. To address this challenge, we propose a novel…

Machine Learning · Computer Science 2025-04-15 Ukjo Hwang , Songnam Hong

Inspired by Double Q-learning algorithm, the Double-DQN (DDQN) algorithm was originally proposed in order to address the overestimation issue in the original DQN algorithm. The DDQN has successfully shown both theoretically and empirically…

Artificial Intelligence · Computer Science 2024-10-30 Shervin Halat , Mohammad Mehdi Ebadzadeh , Kiana Amani

``Distribution shift'' is the main obstacle to the success of offline reinforcement learning. A learning policy may take actions beyond the behavior policy's knowledge, referred to as Out-of-Distribution (OOD) actions. The Q-values for…

Machine Learning · Computer Science 2025-01-14 Jing Zhang , Linjiajie Fang , Kexin Shi , Wenjia Wang , Bing-Yi Jing

$Q$-learning with function approximation is one of the most empirically successful while theoretically mysterious reinforcement learning (RL) algorithms, and was identified in Sutton (1999) as one of the most important theoretical open…

Machine Learning · Computer Science 2022-05-04 Zaiwei Chen , John Paul Clarke , Siva Theja Maguluri

Offline reinforcement learning (RL) is a compelling paradigm to extend RL's practical utility by leveraging pre-collected, static datasets, thereby avoiding the limitations associated with collecting online interactions. The major…

Machine Learning · Computer Science 2024-06-10 Yutaka Shimizu , Joey Hong , Sergey Levine , Masayoshi Tomizuka

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Machine Learning · Computer Science 2026-02-19 Tianyi Chen , Sihan Chen , Xiaoyi Qu , Dan Zhao , Ruomei Yan , Jongwoo Ko , Luming Liang , Pashmina Cameron

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an…

Machine Learning · Computer Science 2021-02-03 Rong Zhu , Mattia Rigotti

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

Machine Learning · Computer Science 2023-11-08 Junmin Zhong , Ruofan Wu , Jennie Si

Alleviating overestimation bias is a critical challenge for deep reinforcement learning to achieve successful performance on more complex tasks or offline datasets containing out-of-distribution data. In order to overcome overestimation…

Machine Learning · Computer Science 2024-01-09 Dohyeok Lee , Seungyub Han , Taehyun Cho , Jungwoo Lee

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks. However, they still suffer two nontrivial obstacles, i.e., low sample efficiency and overestimation bias. To this end, we…

Machine Learning · Computer Science 2022-05-10 Qing Li , Wengang Zhou , Zhenbo Lu , Houqiang Li

Statistical query (SQ) algorithms are algorithms that have access to an {\em SQ oracle} for the input distribution $D$ instead of i.i.d.~ samples from $D$. Given a query function $\phi:X \rightarrow [-1,1]$, the oracle returns an estimate…

Machine Learning · Computer Science 2017-04-18 Vitaly Feldman

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

Neural and Evolutionary Computing · Computer Science 2024-05-01 Sreyes Venkatesh , Razvan Marinescu , Jason K. Eshraghian

Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection and action-evaluation…

Machine Learning · Computer Science 2026-05-18 Prabhat Nagarajan , Martha White , Marlos C. Machado

High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose Offline Stabilization Phases for Efficient Q-Learning…

Machine Learning · Computer Science 2025-03-19 Carlo Romeo , Girolamo Macaluso , Alessandro Sestini , Andrew D. Bagdanov

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting…

Artificial Intelligence · Computer Science 2018-10-23 Scott Fujimoto , Herke van Hoof , David Meger

The goal of this paper is to propose a new Q-learning algorithm with a dummy adversarial player, which is called dummy adversarial Q-learning (DAQ), that can effectively regulate the overestimation bias in standard Q-learning. With the…

Machine Learning · Computer Science 2024-10-01 HyeAnn Lee , Donghwan Lee
‹ Prev 1 2 3 10 Next ›