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
Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning
Indranil Sur, Aswin Raghavan, Abrar Rahman, James Z Hare, Daniel Cassenti, Carl Busart
Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey
Zhihong Liu, Xin Xu, Peng Qiao, Dongsheng Li
Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs
Hubert Szolc, Karol Desnos, Tomasz Kryjak
Towards Active Flow Control Strategies Through Deep Reinforcement Learning
Ricard Montalà, Bernat Font, Pol Suárez, Jean Rabault, Oriol Lehmkuhl, Ivette Rodriguez
Solving Hidden Monotone Variational Inequalities with Surrogate Losses
Ryan D'Orazio, Danilo Vucetic, Zichu Liu, Junhyung Lyle Kim, Ioannis Mitliagkas, Gauthier Gidel
Maximizing User Connectivity in AI-Enabled Multi-UAV Networks: A Distributed Strategy Generalized to Arbitrary User Distributions
Bowei Li, Yang Xu, Ran Zhang, Jiang (Linda)Xie, Miao Wang
Plasticity Loss in Deep Reinforcement Learning: A Survey
Timo Klein, Lukas Miklautz, Kevin Sidak, Claudia Plant, Sebastian Tschiatschek
AllGaits: Learning All Quadruped Gaits and Transitions
Guillaume Bellegarda, Milad Shafiee, Auke Ijspeert