Deep Reinforcement Learning

Deep reinforcement learning (DRL) aims to train agents to make optimal decisions in complex environments by learning through trial and error. Current research focuses on improving DRL's robustness, sample efficiency, and interpretability, often employing architectures like Proximal Policy Optimization (PPO), deep Q-networks (DQNs), and graph neural networks (GNNs) to address challenges in diverse applications such as robotics, game playing, and resource management. The resulting advancements have significant implications for various fields, enabling the development of more adaptable and efficient autonomous systems across numerous domains.

Papers

October 31, 2024

Dual Agent Learning Based Aerial Trajectory Tracking
Shaswat Garg, Houman Masnavi, Baris Fidan, Farrokh Janabi-Sharifi
Deep Reinforcement Learning Unmanned Aerial Vehicle Collision Avoidance Obstacle Avoidance

October 29, 2024

October 27, 2024

October 25, 2024

October 23, 2024

October 22, 2024

October 21, 2024

Deep Reinforcement Learning

Papers

Dual Agent Learning Based Aerial Trajectory Tracking

Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning

From Hype to Reality: The Road Ahead of Deploying DRL in 6G Networks

Self-Driving Car Racing: Application of Deep Reinforcement Learning

Learning Successor Features the Simple Way

Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution

Deep Reinforcement Learning Agents for Strategic Production Policies in Microeconomic Market Simulations

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting

Adversarial Environment Design via Regret-Guided Diffusion Models

MetaTrading: An Immersion-Aware Model Trading Framework for Vehicular Metaverse Services

An Enhanced Hierarchical Planning Framework for Multi-Robot Autonomous Exploration

Entity-based Reinforcement Learning for Autonomous Cyber Defence

Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors

Corrected Soft Actor Critic for Continuous Control

Benchmarking Smoothness and Reducing High-Frequency Oscillations in Continuous Control Policies

RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space

Long-distance Geomagnetic Navigation in GNSS-denied Environments with Deep Reinforcement Learning

Offline reinforcement learning for job-shop scheduling problems

Patrol Security Game: Defending Against Adversary with Freedom in Attack Timing, Location, and Duration