English
Related papers

Related papers: Addressing Maximization Bias in Reinforcement Lear…

200 papers

The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has achieved outstanding performance. However, we find that its…

Machine Learning · Computer Science 2024-06-06 Yu Zhang , Rui Yu , Zhipeng Yao , Wenyuan Zhang , Jun Wang , Liming Zhang

Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation. For translation tasks, rewards can easily be obtained from quality…

Computation and Language · Computer Science 2024-10-15 Gahyun Yoo , Jay Yoon Lee

Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm…

Machine Learning · Computer Science 2024-02-07 Sven Gronauer , Tom Haider , Felippe Schmoeller da Roza , Klaus Diepold

While many algorithmic extensions to Deep Q-Networks (DQN) have been proposed, there remains limited understanding of how different improvements interact. In particular, multi-step and ensemble style extensions have shown promise in…

Machine Learning · Computer Science 2025-06-09 Adrian Ly , Richard Dazeley , Peter Vamplew , Francisco Cruz , Sunil Aryal

Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more…

Machine Learning · Computer Science 2021-07-06 Yao Yao , Li Xiao , Zhicheng An , Wanpeng Zhang , Dijun Luo

We investigate the accuracy of the two most common estimators for the maximum expected value of a general set of random variables: a generalization of the maximum sample average, and cross validation. No unbiased estimator exists and we…

Machine Learning · Statistics 2013-03-04 Hado van Hasselt

Regularized system identification has become a significant complement to more classical system identification. It has been numerically shown that kernel-based regularized estimators often perform better than the maximum likelihood estimator…

Machine Learning · Statistics 2025-03-18 Yue Ju , Bo Wahlberg , Håkan Hjalmarsson

Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent…

Machine Learning · Computer Science 2024-03-11 David Ireland , Giovanni Montana

Maximum likelihood estimation (MLE) is one of the most important methods in machine learning, and the expectation-maximization (EM) algorithm is often used to obtain maximum likelihood estimates. However, EM heavily depends on initial…

Machine Learning · Statistics 2017-11-21 Hideyuki Miyahara , Koji Tsumura , Yuki Sughiyama

Q-learning with value function approximation may have the poor performance because of overestimation bias and imprecise estimate. Specifically, overestimation bias is from the maximum operator over noise estimate, which is exaggerated using…

Machine Learning · Computer Science 2020-06-15 Gang Chen

In this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, \emph{i.e.}, estimating the value function of a model-free Markov reward process using the linear function approximation…

Machine Learning · Computer Science 2018-06-19 Ajin George Joseph , Shalabh Bhatnagar

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation…

Computation and Language · Computer Science 2024-03-19 Zhiwei He , Xing Wang , Wenxiang Jiao , Zhuosheng Zhang , Rui Wang , Shuming Shi , Zhaopeng Tu

We investigate the use of Reinforcement Learning for the optimal execution of meta-orders, where the objective is to execute incrementally large orders while minimizing implementation shortfall and market impact over an extended period of…

Trading and Market Microstructure · Quantitative Finance 2025-11-20 Tomas Espana , Yadh Hafsi , Fabrizio Lillo , Edoardo Vittori

The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment. Recent empirical successes in model-based reinforcement learning with…

Machine Learning · Computer Science 2022-06-07 Dilip Arumugam , Benjamin Van Roy

The overestimation phenomenon caused by function approximation is a well-known issue in value-based reinforcement learning algorithms such as deep Q-networks and DDPG, which could lead to suboptimal policies. To address this issue, TD3…

Machine Learning · Computer Science 2023-11-07 Qiang He , Xinwen Hou

Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization. However, these algorithms may require careful hyperparameter tuning for each problem instance. We use a reinforcement…

Machine Learning · Computer Science 2021-03-22 Dmitrii Beloborodov , A. E. Ulanov , Jakob N. Foerster , Shimon Whiteson , A. I. Lvovsky

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can…

Machine Learning · Computer Science 2015-12-10 Hado van Hasselt , Arthur Guez , David Silver

In Reinforcement Learning the Q-learning algorithm provably converges to the optimal solution. However, as others have demonstrated, Q-learning can also overestimate the values and thereby spend too long exploring unhelpful states. Double…

Machine Learning · Computer Science 2023-03-16 David Barber

Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the exploration potential of double actors remains underexplored.…

Machine Learning · Computer Science 2025-11-21 Haohui Chen , Zhiyong Chen , Aoxiang Liu , Wentuo Fang

Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation. Its variants in the deep Q-learning paradigm have shown great promise in producing…

Machine Learning · Computer Science 2022-01-17 Zhizhou Ren , Guangxiang Zhu , Hao Hu , Beining Han , Jianglun Chen , Chongjie Zhang