DQN Agent

Deep Q-Networks (DQNs) are a core deep reinforcement learning algorithm aiming to learn optimal action-selection policies by approximating the Q-function, which estimates the expected future reward for each action in a given state. Current research focuses on improving DQN's efficiency and robustness, including exploring novel architectures like incorporating transformers and addressing challenges such as catastrophic interference, sparse rewards, and limited data. These advancements are significant for various applications, from autonomous systems and robotics to optimizing resource allocation in complex environments like traffic control and renewable energy integration, by enabling more efficient and reliable learning in challenging real-world scenarios.

Papers

October 14, 2024

Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement Learning
William A. Stigall
Reinforcement Learning Deep Q Network Architecture Perspective DQN Agent

August 15, 2024

Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators
Mark Towers, Yali Du, Christopher Freeman, Timothy J. Norman
Agent Smith Agent Behavior DQN Agent Future Prediction

August 2, 2024

Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems
Juan C. Rosero, Ivana Dusparic, Nicolás Cardozo
Reinforcement Learning Q Learning Autonomous System Multi Objective Optimization Multi Objective Reinforcement Learning Optimization Process DQN Agent Multi Objective Deep Reinforcement Learning

July 22, 2024

Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN
Norman Becker, Daniel Reti, Evridiki V. Ntagiou, Marcus Wallum, Hans D. Schotten
Reinforcement Learning Q Learning DQN Agent Penetration Testing

July 10, 2024

CM-DQN: A Value-Based Deep Reinforcement Learning Model to Simulate Confirmation Bias
Jiacheng Shen, Lihan Feng
Deep Reinforcement Learning DQN Agent Confirmation Bias Value Based Deep Reinforcement Learning

July 5, 2024

Simplifying Deep Temporal Difference Learning
Matteo Gallici, Mattie Fellows, Benjamin Ellis, Bartomeu Pou, Ivan Masmitja, Jakob Nicolaus Foerster, Mario Martin
Q Learning Temporal Difference Learning DQN Agent Replay Buffer

June 14, 2024

A Benchmark for Maximum Cut: Towards Standardization of the Evaluation of Learned Heuristics for Combinatorial Optimization
Ankur Nath, Alan Kuhnle
New Benchmark Global Evaluation Combinatorial Optimization Problem Simple Heuristic DQN Agent Cut Problem

April 2, 2024

K-percent Evaluation for Lifelong RL
Golnaz Mesbahi, Parham Mohammad Panahi, Olya Mastikhina, Martha White, Adam White
Deep RL DQN Agent Continual Reinforcement Learning Lifelong Reinforcement Learning

February 25, 2024

Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis
Qishuo Cheng, Le Yang, Jiajian Zheng, Miao Tian, Duan Xin
Deep Learning Predictive Model DQN Agent Risk Assessment Portfolio Management Q Value Digital Asset

January 6, 2024

Semi-supervised learning via DQN for log anomaly detection
Yingying He, Xiaobing Pei, Lihong Shen
Semi Supervised DQN Agent Log Anomaly Detection Supervised Anomaly Detection

December 13, 2023

The Effective Horizon Explains Deep RL Performance in Stochastic Environments
Cassidy Laidlaw, Banghua Zhu, Stuart Russell, Anca Dragan
Reinforcement Learning Deep Reinforcement Learning DQN Agent Stochastic Environment Exploration Algorithm Reinforcement Learning Performance

December 5, 2023

Lights out: training RL agents robust to temporary blindness
N. Ordonez, M. Tromp, P. M. Julbe, W. Böhmer
Loss Function Optimal Policy DQN Agent Hidden Representation RL Agent Blind User

October 28, 2023

Weakly Coupled Deep Q-Networks
Ibrahim El Shar, Daniel R. Jiang
Deep Reinforcement Learning Q Learning Deep Q Network DQN Agent Double DQN

September 29, 2023

Reliability Quantification of Deep Reinforcement Learning-based Control
Hitoshi Yoshioka, Hirotada Hashimoto
Deep Reinforcement Learning DQN Agent Deep Reinforcement Learning Based Reliability Analysis Reliability Evaluation

September 25, 2023

Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation
Zihang Wang, Maowei Jiang
Reinforcement Learning DQN Agent Data Efficiency Mesh Network

August 28, 2023

Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning
Longchao Da, Minquan Gao, Hao Mei, Hua Wei
Reinforcement Learning Prompt Learning Formality Transfer Style PROMPT Traffic Signal Control DQN Agent Traffic Dynamic Trained Policy

August 16, 2023

Integrating Renewable Energy in Agriculture: A Deep Reinforcement Learning-based Approach
A. Wahid, I faiud, K. Mason
Deep Q Network Deep Reinforcement Learning Based Approach Agricultural Domain Renewable Energy DQN Agent Photovoltaic Power

August 1, 2023

Pixel to policy: DQN Encoders for within & cross-game reinforcement learning
Ashrya Agrawal, Priyanshi Shah, Sourabh Prakash
Reinforcement Learning Transfer Learning Tetromino Pixel DQN Agent Cross Domain Reinforcement Learning

July 26, 2023

Research on Inertial Navigation Technology of Unmanned Aerial Vehicles with Integrated Reinforcement Learning Algorithm
Longcheng Guo
Reinforcement Learning Unmanned Aerial Vehicle Autonomous Navigation Dynamic Environment DH Research Intelligent Agent DQN Agent Inertial Navigation System Inertial Navigation

July 10, 2023

Measuring and Mitigating Interference in Reinforcement Learning
Vincent Liu, Han Wang, Ruo Yu Tao, Khurram Javed, Adam White, Martha White
Reinforcement Learning Measurement System Catastrophic Interference DQN Agent Value Based Reinforcement Learning Interference Mitigation

DQN Agent

Papers

Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement Learning

Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators

Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems

Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN

CM-DQN: A Value-Based Deep Reinforcement Learning Model to Simulate Confirmation Bias

Simplifying Deep Temporal Difference Learning

A Benchmark for Maximum Cut: Towards Standardization of the Evaluation of Learned Heuristics for Combinatorial Optimization

K-percent Evaluation for Lifelong RL

Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis

Semi-supervised learning via DQN for log anomaly detection

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

Lights out: training RL agents robust to temporary blindness

Weakly Coupled Deep Q-Networks

Reliability Quantification of Deep Reinforcement Learning-based Control

Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation

Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning

Integrating Renewable Energy in Agriculture: A Deep Reinforcement Learning-based Approach

Pixel to policy: DQN Encoders for within & cross-game reinforcement learning

Research on Inertial Navigation Technology of Unmanned Aerial Vehicles with Integrated Reinforcement Learning Algorithm

Measuring and Mitigating Interference in Reinforcement Learning