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

March 21, 2024

DouRN: Improving DouZero by Residual Neural Networks
Yiquan Chen, Yingchao Lyu, Di Zhang
Deep Reinforcement Learning Multi Layer Residual Neural Network Normal Form Game Poker Hand DouDizhu AI

March 19, 2024

March 18, 2024

Demystifying the Physics of Deep Reinforcement Learning-Based Autonomous Vehicle Decision-Making
Hanxi Wan, Pei Li, Arpan Kusari
Reinforcement Learning Deep Reinforcement Learning Autonomous Vehicle Theoretical Physic Deep Reinforcement Vehicle Decision Making

March 16, 2024

Deep Reinforcement Learning-based Large-scale Robot Exploration
Yuhong Cao, Rui Zhao, Yizhuo Wang, Bairan Xiang, Guillaume Sartoretti
Deep Reinforcement Learning Deep Reinforcement Neural Planner Large Scale LiDAR

March 15, 2024

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
Luca Grillotti, Maxence Faldor, Borja G. León, Antoine Cully
Deep Reinforcement Learning Value Function Net Present Value Quality Diversity High Performance Diverse Behavior Policy Actor Critic Successor Feature

March 14, 2024

March 13, 2024

Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning
Ángel Aso-Mollar, Eva Onaindia
Reinforcement Learning Deep Reinforcement Learning Markov Decision Process Task Planning Generalized Planning Action Space Reinforcement Learning

March 12, 2024

March 11, 2024

March 10, 2024

Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning
Vikram Goddla
Deep Reinforcement Learning Low Rank Decomposition Regularized Reinforcement Learning Deep Policy

March 9, 2024

March 8, 2024

Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking
Robert Reed, Hanspeter Schaub, Morteza Lahijanian
Deep Reinforcement Learning Temporal Logic Unmanned Spacecraft Autonomous Spacecraft

March 7, 2024

Model-Free Load Frequency Control of Nonlinear Power Systems Based on Deep Reinforcement Learning
Xiaodi Chen, Meng Zhang, Zhengguang Wu, Ligang Wu, Xiaohong Guan
Deep Reinforcement Learning Power System Frequency Control

Deep Reinforcement Learning

Papers

DouRN: Improving DouZero by Residual Neural Networks

Fast Value Tracking for Deep Reinforcement Learning

Bin Packing Optimization via Deep Reinforcement Learning

Demystifying the Physics of Deep Reinforcement Learning-Based Autonomous Vehicle Decision-Making

Deep Reinforcement Learning-based Large-scale Robot Exploration

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

Socially Integrated Navigation: A Social Acting Robot with Deep Reinforcement Learning

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

Leveraging Constraint Programming in a Deep Learning Approach for Dynamically Solving the Flexible Job-Shop Scheduling Problem

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning

Deep Reinforcement Learning for Modelling Protein Complexes

Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward

Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning

Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence

UDCR: Unsupervised Aortic DSA/CTA Rigid Registration Using Deep Reinforcement Learning and Overlap Degree Calculation

Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking

Model-Free Load Frequency Control of Nonlinear Power Systems Based on Deep Reinforcement Learning