中文
相关论文

相关论文: Enhancing Q-Value Updates in Deep Q-Learning via S…

200 篇论文

Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge…

机器学习 · 计算机科学 2023-04-19 Kavosh Asadi , Rasool Fakoor , Omer Gottesman , Taesup Kim , Michael L. Littman , Alexander J. Smola

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

机器学习 · 计算机科学 2019-05-01 Sam Green , Craig M. Vineyard , Çetin Kaya Koç

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research…

软件工程 · 计算机科学 2021-12-07 Basel Magableh

Deep reinforcement learning can learn effective policies for a wide range of tasks, but is notoriously difficult to use due to instability and sensitivity to hyperparameters. The reasons for this remain unclear. When using standard…

机器学习 · 计算机科学 2020-03-17 Aviral Kumar , Abhishek Gupta , Sergey Levine

We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole…

机器学习 · 计算机科学 2019-11-13 Su Young Lee , Sungik Choi , Sae-Young Chung

Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are…

机器学习 · 计算机科学 2021-08-24 Nishanth Anand , Doina Precup

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…

机器学习 · 计算机科学 2026-05-18 Prabhat Nagarajan , Martha White , Marlos C. Machado

We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to…

机器人学 · 计算机科学 2019-07-31 Tianyu Shi , Pin Wang , Xuxin Cheng , Ching-Yao Chan , Ding Huang

With the development of experimental quantum technology, quantum control has attracted increasing attention due to the realization of controllable artificial quantum systems. However, because quantum-mechanical systems are often too…

量子物理 · 物理学 2022-12-22 Zhikang Wang

Recent advancements in deep reinforcement learning (DRL) techniques have sparked its multifaceted applications in the automation sector. Managing complex decision-making problems with DRL encourages its use in the nuclear industry for tasks…

人工智能 · 计算机科学 2026-02-19 Biswajit Sadhu , Trijit Sadhu , S. Anand

State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the…

机器学习 · 统计学 2024-12-17 Jiahe Lin , George Michailidis

In this paper, we build on advances introduced by the Deep Q-Networks (DQN) approach to extend the multi-objective tabular Reinforcement Learning (RL) algorithm W-learning to large state spaces. W-learning algorithm can naturally solve the…

机器学习 · 计算机科学 2023-06-27 Jernej Hribar , Luke Hackett , Ivana Dusparic

An improvement of Q-learning is proposed in this paper. It is different from classic Q-learning in that the similarity between different states and actions is considered in the proposed method. During the training, a new updating mechanism…

人工智能 · 计算机科学 2021-06-03 Wei Liao , Xiaohui Wei , Jizhou Lai

In this work, the trick-taking game Wizard with a separate bidding and playing phase is modeled by two interleaved partially observable Markov decision processes (POMDP). Deep Q-Networks (DQN) are used to empower self-improving agents,…

机器学习 · 计算机科学 2022-05-30 Jonas Schumacher , Marco Pleines

Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert…

机器学习 · 计算机科学 2021-07-09 Si-An Chen , Voot Tangkaratt , Hsuan-Tien Lin , Masashi Sugiyama

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…

机器学习 · 计算机科学 2024-06-10 Yutaka Shimizu , Joey Hong , Sergey Levine , Masayoshi Tomizuka

Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL)…

机器学习 · 计算机科学 2026-03-10 Alkis Sygkounas , Ioannis Athanasiadis , Andreas Persson , Michael Felsberg , Amy Loutfi

We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in…

机器学习 · 计算机科学 2018-02-20 Petros Giannakopoulos , Yannis Cotronis

Deep Reinforcement Learning (DRL) has shown outstanding performance on inducing effective action policies that maximize expected long-term return on many complex tasks. Much of DRL work has been focused on sequences of events with discrete…

机器学习 · 计算机科学 2021-05-07 Yeo Jin Kim , Min Chi

Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the…

机器学习 · 计算机科学 2024-03-26 Aditya Bhatt , Daniel Palenicek , Boris Belousov , Max Argus , Artemij Amiranashvili , Thomas Brox , Jan Peters