Deep Q

Deep Q-learning (DQL) is a reinforcement learning algorithm using deep neural networks to approximate optimal action-value functions, aiming to train agents to make optimal decisions in complex environments. Current research focuses on improving DQL's efficiency and robustness through techniques like federated learning for distributed systems, incorporating curiosity-driven exploration, and employing model architectures such as Deep Recurrent Q-Networks and Deep Deterministic Policy Gradients to handle diverse tasks and data types. These advancements are impacting various fields, including autonomous systems (e.g., self-driving cars, UAV navigation), resource optimization (e.g., network load balancing, resource scheduling), and even quantum computing, demonstrating DQL's broad applicability and potential for solving challenging real-world problems.

Papers

February 13, 2024

Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment
Sagar Pathak, Bidhya Shrestha, Kritish Pahi
Global Evaluation Practical Implementation Deep Q Learning Self Driving Car Deep Q Deep Learning Track

February 10, 2024

Federated Deep Q-Learning and 5G load balancing
Hsin Lin, Yi-Kang Su, Hong-Qi Chen, La-Fei Ko
Deep Q Learning Deep Q Dynamic Loading

February 1, 2024

Neural Policy Style Transfer
Raul Fernandez-Fernandez, Juan G. Victores, Jennifer J. Gago, David Estevez, Carlos Balaguer
Deep Reinforcement Learning Style Transfer Deep Q

January 31, 2024

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning
Xuecheng Niu, Akinori Ito, Takashi Nose
Reinforcement Learning Efficient Exploration Deep Q Task Oriented Dialog Artificial Curiosity Dialog Policy Learning

January 25, 2024

Learning When to See for Long-term Traffic Data Collection on Power-constrained Devices
Ruixuan Zhang, Wenyu Han, Zilin Bian, Kaan Ozbay, Chen Feng
LeArning Abstract Recurrent Neural Network Kalman Filter Traffic Data Resource Constrained Device Deep Q Optimal Timing

January 21, 2024

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
Rodrigo Coelho, André Sequeira, Luís Paulo Santos
Reinforcement Learning System Performance Reinforcement Learning Algorithm Variational Quantum Circuit Deep Q Learning Deep Q

November 24, 2023

Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery
Ekaterina Nikonova, Cheng Xue, Jochen Renz
Deep Reinforcement Learning Knowledge Distillation AI Agent Open World Deep Reinforcement Deep Q Rule Discovery

October 7, 2023

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network
Zhenyu Tao, Wei Xu, Xiaohu You
Deep Reinforcement Learning Markov Decision Process Digital Twin Deep Q Network Slice Admission Control

April 27, 2023

BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading
Maniraman Periyasamy, Marc Hölle, Marco Wiedmann, Daniel D. Scherer, Axel Plinge, Christopher Mutschler
Deep Reinforcement Learning Quantum Computing Deep Q Batch Reinforcement Learning

April 19, 2023

Learning Resource Scheduling with High Priority Users using Deep Deterministic Policy Gradients
Steffen Gracla, Edgar Beck, Carsten Bockelmann, Armin Dekorsy
Resource Allocation Deep Deterministic Policy Gradient Resource Management Priority User Deep Q Asymmetric Counterfactual Utility

April 11, 2023

RELS-DQN: A Robust and Efficient Local Search Framework for Combinatorial Optimization
Yuanhang Shao, Tonmoy Dey, Nikola Vuckovic, Luke Van Popering, Alan Kuhnle
Local Search Deep Q Learning Deep Q

March 16, 2023

Self-Inspection Method of Unmanned Aerial Vehicles in Power Plants Using Deep Q-Network Reinforcement Learning
Haoran Guan
Reinforcement Learning Unmanned Aerial Vehicle Q Learning Deep Q Network Deep Q Self Checking

November 9, 2022

Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning
Jernej Hribar, Luke Hackett, Ivana Dusparic
Deep Reinforcement Learning Deep Q Network Multi Objective Reinforcement Learning Deep Q Multi Objective Optimisation

October 3, 2022

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders
Per-Arne Andersen, Ole-Christoffer Granmo, Morten Goodwin
Reinforcement Learning Deep Reinforcement Learning Variational Autoencoders Deep Q Learning Deep Q Option Discovery Option Learning

June 15, 2022

A Search-Based Testing Approach for Deep Reinforcement Learning Agents
Amirhossein Zolfagharian, Manel Abdellatif, Lionel Briand, Mojtaba Bagherzadeh, Ramesh S
Deep Reinforcement Learning Reinforcement Learning Agent Search Based Deep Q

May 19, 2022

Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changes
Eric Chalmers, Artur Luczak
Reinforcement Learning Adaptation Concern Digital Modulation Deep Q Biological Learning Environmental Change Reward Misspecification

April 24, 2022

Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing
Victor Augusto Kich, Junior Costa de Jesus, Ricardo Bedin Grando, Alisson Henrique Kolling, Gabriel Vinícius Heisler, Rodrigo da Silva Guerra
Deep Reinforcement Learning High Dimensional Neural Network Policy Deep Q Visual Complexity

April 1, 2022

Deep Q-learning of global optimizer of multiply model parameters for viscoelastic imaging
Hongmei Zhang, Kai Wang, Yan Zhou, Shadab Momin, Xiaofeng Yang, Mostafa Fatemi, Michael F. Insana
Global Optimization Deep Q Learning Model Parameter Deep Q Global Optimum Shear Wave

March 30, 2022

Investigating the Properties of Neural Network Representations in Reinforcement Learning
Han Wang, Erfan Miahi, Martha White, Marlos C. Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White
Reinforcement Learning Deep Reinforcement Learning Many Property Neural Network Representation Deep Q

January 6, 2022

Sales Time Series Analytics Using Deep Q-Learning
Bohdan M. Pavlyshenko
Q Learning Deep Q Learning Deep Q

Deep Q

Papers

Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment

Federated Deep Q-Learning and 5G load balancing

Neural Policy Style Transfer

Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning

Learning When to See for Long-term Traffic Data Collection on Power-constrained Devices

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability

Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network

BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading

Learning Resource Scheduling with High Priority Users using Deep Deterministic Policy Gradients

RELS-DQN: A Robust and Efficient Local Search Framework for Combinatorial Optimization

Self-Inspection Method of Unmanned Aerial Vehicles in Power Plants Using Deep Q-Network Reinforcement Learning

Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

A Search-Based Testing Approach for Deep Reinforcement Learning Agents

Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changes

Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing

Deep Q-learning of global optimizer of multiply model parameters for viscoelastic imaging

Investigating the Properties of Neural Network Representations in Reinforcement Learning

Sales Time Series Analytics Using Deep Q-Learning