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 26, 2023

Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion
Laura Smith, Yunhao Cao, Sergey Levine
Deep Reinforcement Learning Continuum Limit Quadrupedal Robot Efficient Exploration Legged Locomotion Robot Locomotion Real World Reinforcement Learning Policy Regularization Continuous Improvement

October 25, 2023

October 24, 2023

October 23, 2023

October 22, 2023

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization
Jinbiao Chen, Jiahai Wang, Zizhen Zhang, Zhiguang Cao, Te Ye, Siyuan Chen
Deep Reinforcement Learning Neural Network Heuristic Multi Objective Combinatorial Optimization Efficient Meta

October 21, 2023

October 20, 2023

October 18, 2023

Learning to Optimise Climate Sensor Placement using a Transformer
Chen Wang, Victoria Huang, Gang Chen, Hui Ma, Bryce Chen, Jochen Schmidt
LeArning Abstract Deep Reinforcement Learning Transformer Based Actor Critic Algorithm Sensor Placement

Deep Reinforcement Learning

Papers

Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion

Conditionally Combining Robot Skills using Large Language Models

Imperfect Digital Twin Assisted Low Cost Reinforcement Training for Multi-UAV Networks

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

State Sequences Prediction via Fourier Transform for Representation Learning

Solving the flexible job-shop scheduling problem through an enhanced deep reinforcement learning approach

Graph Attention-based Deep Reinforcement Learning for solving the Chinese Postman Problem with Load-dependent costs

Fractal Landscapes in Policy Optimization

Mind the Model, Not the Agent: The Primacy Bias in Model-based RL

Diverse Priors for Deep Reinforcement Learning

Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior

One is More: Diverse Perspectives within a Single Network for Efficient DRL

Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques

Reward Shaping for Happier Autonomous Cyber Security Agents

Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation

RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

Learning to Optimise Climate Sensor Placement using a Transformer