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
DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training
Aleksei Petrenko, Arthur Allshire, Gavriel State, Ankur Handa, Viktor Makoviychuk
Game-Theoretical Analysis of Reviewer Rewards in Peer-Review Journal Systems: Analysis and Experimental Evaluation using Deep Reinforcement Learning
Minhyeok Lee
Lyapunov-Driven Deep Reinforcement Learning for Edge Inference Empowered by Reconfigurable Intelligent Surfaces
Kyriakos Stylianopoulos, Mattia Merluzzi, Paolo Di Lorenzo, George C. Alexandropoulos
Automatic Design Method of Building Pipeline Layout Based on Deep Reinforcement Learning
Chen Yang, Zhe Zheng, Jia-Rui Lin
An Intelligent SDWN Routing Algorithm Based on Network Situational Awareness and Deep Reinforcement Learning
Jinqiang Li, Miao Ye, Linqiang Huang, Xiaofang Deng, Hongbing Qiu, Yong Wang
Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving
Weitao Zhou, Zhong Cao, Nanshan Deng, Kun Jiang, Diange Yang
Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms
Jinyang Jiang, Jiaqiao Hu, Yijie Peng
Deep Reinforcement Learning for Interference Management in UAV-based 3D Networks: Potentials and Challenges
Mojtaba Vaezi, Xingqin Lin, Hongliang Zhang, Walid Saad, H. Vincent Poor
Optimizing Memory Mapping Using Deep Reinforcement Learning
Pengming Wang, Mikita Sazanovich, Berkin Ilbeyi, Phitchaya Mangpo Phothilimthana, Manish Purohit, Han Yang Tay, Ngân Vũ, Miaosen Wang, Cosmin Paduraru, Edouard Leurent, Anton Zhernov, Po-Sen Huang, Julian Schrittwieser, Thomas Hubert, Robert Tung, Paula Kurylowicz, Kieran Milan, Oriol Vinyals, Daniel J. Mankowitz
Assessment of Reinforcement Learning Algorithms for Nuclear Power Plant Fuel Optimization
Paul Seurin, Koroush Shirvan
Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement
Yunke Ao, Hooman Esfandiari, Fabio Carrillo, Yarden As, Mazda Farshad, Benjamin F. Grewe, Andreas Krause, Philipp Fuernstahl
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
Jiajun Fan, Yuzheng Zhuang, Yuecheng Liu, Jianye Hao, Bin Wang, Jiangcheng Zhu, Hao Wang, Shu-Tao Xia
Cooperating Graph Neural Networks with Deep Reinforcement Learning for Vaccine Prioritization
Lu Ling, Washim Uddin Mondal, Satish V, Ukkusuri