English
Related papers

Related papers: WD3: Taming the Estimation Bias in Deep Reinforcem…

200 papers

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

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is formulated theoretically as the expected returns discounted…

Machine Learning · Computer Science 2023-02-13 Haoxuan Pan , Deheng Ye , Xiaoming Duan , Qiang Fu , Wei Yang , Jianping He , Mingfei Sun

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty.…

Machine Learning · Computer Science 2023-07-06 Takuya Kanazawa , Haiyan Wang , Chetan Gupta

Data valuation quantifies data importance, but existing methods cannot ensure validity in a single training process. The neural dynamic data valuation (NDDV) method [3] addresses this limitation. Based on NDDV, we are the first to explore…

Machine Learning · Computer Science 2025-12-19 Zhangyong Liang , Huanhuan Gao , Ji Zhang

Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…

Machine Learning · Computer Science 2026-02-11 Qingnan Ren , Shiting Huang , Zhen Fang , Zehui Chen , Lin Chen , Lijun Li , Feng Zhao

Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on…

Machine Learning · Computer Science 2026-01-29 Zhizheng Jiang , Kang Zhao , Weikai Xu , Xinkui Lin , Wei Liu , Jian Luan , Shuo Shang , Peng Han

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

Ensuring fairness in machine learning is a critical and challenging task, as biased data representations often lead to unfair predictions. To address this, we propose Deep Fair Learning, a framework that integrates nonlinear sufficient…

Machine Learning · Statistics 2025-04-10 Enze Shi , Linglong Kong , Bei Jiang

In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and…

Machine Learning · Computer Science 2020-01-10 Whiyoung Jung , Giseung Park , Youngchul Sung

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new…

Machine Learning · Computer Science 2019-11-06 Ofir Nachum , Yinlam Chow , Bo Dai , Lihong Li

Electric Vehicles (EVs) offer substantial flexibility for grid services, yet large-scale, uncoordinated charging can threaten voltage stability in distribution networks. Existing Reinforcement Learning (RL) approaches for smart charging…

Systems and Control · Electrical Eng. & Systems 2025-10-23 Stavros Orfanoudakis , Frans A. Oliehoek , Peter Palensky , Pedro P. Vergara

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Machine Learning · Computer Science 2020-11-20 Jonathan N. Lee , Aldo Pacchiano , Vidya Muthukumar , Weihao Kong , Emma Brunskill

Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose Generalized…

Machine Learning · Computer Science 2023-03-07 Edoardo Cetin , Oya Celiktutan

Machine learning for scientific applications faces the challenge of limited data. We propose a framework that leverages a priori known physics to reduce overfitting when training on relatively small datasets. A deep neural network is…

Machine Learning · Computer Science 2019-11-22 Jonathan B. Freund , Jonathan F. MacArt , Justin Sirignano

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 continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Conversely, evolutionary and developmental methods focusing on…

Machine Learning · Computer Science 2018-09-21 Cédric Colas , Olivier Sigaud , Pierre-Yves Oudeyer

We consider the emphatic temporal-difference (TD) algorithm, ETD($\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\lambda$) algorithm was recently…

Machine Learning · Computer Science 2017-01-23 Huizhen Yu

Often, what is termed algorithmic bias in machine learning will be due to historic bias in the training data. But sometimes the bias may be introduced (or at least exacerbated) by the algorithm itself. The ways in which algorithms can…

Machine Learning · Computer Science 2021-04-20 Padraig Cunningham , Sarah Jane Delany

The boom of Generative AI brings opportunities entangled with risks and concerns. Existing literature emphasizes the generalization capability of deepfake detection on unseen generators, significantly promoting the detector's ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yongqi Yang , Zhihao Qian , Ye Zhu , Olga Russakovsky , Yu Wu