English
Related papers

Related papers: Qualitative Measurements of Policy Discrepancy for…

200 papers

Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer. However, the target updates in DQN often rely on next states generated by actions from past, potentially suboptimal, policy. As a…

Machine Learning · Computer Science 2025-11-07 Lipeng Zu , Hansong Zhou , Xiaonan Zhang

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

Machine Learning · Computer Science 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in…

Multiagent Systems · Computer Science 2018-04-17 Yan Zheng , Jianye Hao , Zongzhang Zhang

Model-based reinforcement learning uses models to plan, where the predictions and policies of an agent can be improved by using more computation without additional data from the environment, thereby improving sample efficiency. However,…

Machine Learning · Computer Science 2023-02-22 Animesh Kumar Paul , Videh Raj Nema

Reinforcement learning methods typically use Deep Neural Networks to approximate the value functions and policies underlying a Markov Decision Process. Unfortunately, DNN-based RL suffers from a lack of explainability of the resulting…

Systems and Control · Electrical Eng. & Systems 2022-05-19 Shambhuraj Sawant , Sebastien Gros

How to implement multi-qubit gates efficiently with high precision is essential for realizing universal fault tolerant computing. For a physical system with some external controllable parameters, it is a great challenge to control the time…

Quantum Physics · Physics 2019-07-24 Zheng An , D. L. Zhou

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

For the purpose of inspecting power plants, autonomous robots can be built using reinforcement learning techniques. The method replicates the environment and employs a simple reinforcement learning (RL) algorithm. This strategy might be…

Robotics · Computer Science 2023-03-17 Haoran Guan

The deep reinforcement learning method usually requires a large number of training images and executing actions to obtain sufficient results. When it is extended a real-task in the real environment with an actual robot, the method will be…

Computer Vision and Pattern Recognition · Computer Science 2018-06-05 Daiki Kimura

Reinforcement Learning can be applied to various tasks, and environments. Many of these environments have a similar shared structure, which can be exploited to improve RL performance on other tasks. Transfer learning can be used to take…

Machine Learning · Computer Science 2023-08-02 Ashrya Agrawal , Priyanshi Shah , Sourabh Prakash

Owing to the openness of wireless channels, wireless communication systems are highly susceptible to malicious jamming. Most existing anti-jamming methods rely on the assumption of accurate sensing and optimize parameters on a single…

Information Theory · Computer Science 2025-11-06 Haoqin Zhao , Zan Li , Jiangbo Si , Rui Huang , Hang Hu , Tony Q. S. Quek , Naofal Al-Dhahir

Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation.…

Machine Learning · Computer Science 2019-03-22 Joshua Achiam , Ethan Knight , Pieter Abbeel

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions…

Artificial Intelligence · Computer Science 2017-10-09 Matteo Hessel , Joseph Modayil , Hado van Hasselt , Tom Schaul , Georg Ostrovski , Will Dabney , Dan Horgan , Bilal Piot , Mohammad Azar , David Silver

With the rapid growth of memory and computing power, datasets are becoming increasingly complex and imbalanced. This is especially severe in the context of clinical data, where there may be one rare event for many cases in the majority…

Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies leverage Reinforcement Learning (RL) to address DAC challenges; however, applying RL…

Machine Learning · Computer Science 2026-04-03 Tai Nguyen , Phong Le , André Biedenkapp , Carola Doerr , Nguyen Dang

The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall…

Machine Learning · Computer Science 2025-04-04 Théo Vincent , Daniel Palenicek , Boris Belousov , Jan Peters , Carlo D'Eramo

In this thesis, we consider two simple but typical control problems and apply deep reinforcement learning to them, i.e., to cool and control a particle which is subject to continuous position measurement in a one-dimensional quadratic…

Quantum Physics · Physics 2022-12-15 Zhikang Wang

This paper presents a Double Deep Q-Network algorithm for trading single assets, namely the E-mini S&P 500 continuous futures contract. We use a proven setup as the foundation for our environment with multiple extensions. The features of…

Machine Learning · Computer Science 2022-06-30 Frensi Zejnullahu , Maurice Moser , Joerg Osterrieder

NDN has gained significant attention due to the appearance of several unforeseen design flaws that became evident with new communication scenarios. Among its many features, the two standard NDN forwarding strategies are not adaptive,…

Networking and Internet Architecture · Computer Science 2020-10-21 Ygor Amaral B. L. de Sena , Kelvin Lopes Dias , Cleber Zanchettin

Reinforcement learning with neural networks (RLNN) has recently demonstrated great promise for many problems, including some problems in quantum information theory. In this work, we apply RLNN to quantum hypothesis testing and determine the…

Quantum Physics · Physics 2022-01-26 Sarah Brandsen , Kevin D. Stubbs , Henry D. Pfister