English
Related papers

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

200 papers

We study the policy evaluation problem in multi-agent reinforcement learning. In this problem, a group of agents works cooperatively to evaluate the value function for the global discounted accumulative reward problem, which is composed of…

Optimization and Control · Mathematics 2019-06-04 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

In many scientific and engineering problems, noise and nonlinearity are unavoidable, which could induce interesting mathematical problem such as transition phenomena. This paper focuses on efficiently discovering the most probable…

Optimization and Control · Mathematics 2023-06-08 Jin Guo , Ting Gao , Peng Zhang , Jiequn Han , Jinqiao Duan

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootstrapping, i.e. they update the value function toward a learning target using value estimates at…

Machine Learning · Computer Science 2022-01-07 Anthony GX-Chen , Veronica Chelu , Blake A. Richards , Joelle Pineau

Value function approximation has demonstrated phenomenal empirical success in reinforcement learning (RL). Nevertheless, despite a handful of recent progress on developing theory for RL with linear function approximation, the understanding…

Machine Learning · Computer Science 2020-06-22 Ruosong Wang , Ruslan Salakhutdinov , Lin F. Yang

Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited,…

Machine Learning · Computer Science 2021-02-12 Botao Hao , Nevena Lazic , Yasin Abbasi-Yadkori , Pooria Joulani , Csaba Szepesvari

Deep learning has shown successful application in visual recognition and certain artificial intelligence tasks. Deep learning is also considered as a powerful tool with high flexibility to approximate functions. In the present work,…

Machine Learning · Computer Science 2021-12-23 Ayan Chakraborty , Thomas Wick , Xiaoying Zhuang , Timon Rabczuk

This paper makes one step forward towards characterizing a new family of \textit{model-free} Deep Reinforcement Learning (DRL) algorithms. The aim of these algorithms is to jointly learn an approximation of the state-value function ($V$),…

Machine Learning · Computer Science 2019-10-15 Matthia Sabatelli , Gilles Louppe , Pierre Geurts , Marco A. Wiering

We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal…

Artificial Intelligence · Computer Science 2018-11-21 Felix Leibfried , Jordi Grau-Moya , Haitham Bou-Ammar

Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to…

Machine Learning · Computer Science 2023-02-21 Enrico Marchesini , Christopher Amato

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…

Machine Learning · Statistics 2026-05-08 Joseph H. Rudoler , Kevin Tan , Giles Hooker , Konrad P. Kording

Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to…

Machine Learning · Computer Science 2020-03-02 Adithya M. Devraj , Ioannis Kontoyiannis , Sean P. Meyn

TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value…

Machine Learning · Computer Science 2025-12-24 Lex Weaver , Jonathan Baxter

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

This paper investigates the use of prior computation to estimate the value function to improve sample efficiency in on-policy policy gradient methods in reinforcement learning. Our approach is to estimate the value function from prior…

Machine Learning · Computer Science 2023-02-06 Md Masudur Rahman , Yexiang Xue

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Machine Learning · Computer Science 2018-11-07 Jalaj Bhandari , Daniel Russo , Raghav Singal

With the high development of wireless communication techniques, it is widely used in various fields for convenient and efficient data transmission. Different from commonly used assumption of the time-invariant wireless channel, we focus on…

Information Theory · Computer Science 2020-11-10 Mengfan Liu , Rui Wang

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Machine Learning · Computer Science 2023-03-20 Nicolai Dorka , Tim Welschehold , Wolfram Burgard

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that…

Machine Learning · Computer Science 2020-01-27 Shangtong Zhang , Wendelin Boehmer , Shimon Whiteson

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…