A hierarchical navigation decision-making method for UAV swarms in unknown communication-constrained environments. [PDF]
PLoS OneXiong H, Yu B, Zhang J, Dong H.
europepmc +1 more source
A hierarchical multi‑timescale reinforcement learning framework for hybrid energy storage management with aging‑aware constraint adaptation. [PDF]
Sci RepMohammadbeigi M +2 more
europepmc +1 more source
Dynamic Traffic Signal Control for Isolated Intersections: Enhanced SARSA Reinforcement Learning with Expectation Prediction and Eligibility Traces. [PDF]
Sensors (Basel)Gao Y, Sun W, Jian M, Zhang Z, Yan Z.
europepmc +1 more source
Closed-Loop digital therapeutics empowered by deep reinforcement learning and wearable sensing for precision orthopedic rehabilitation: a simulation-based proof-of-concept study. [PDF]
Front Rehabil SciDong J, Chen T, Peng Z.
europepmc +1 more source
Related searches:
Learning to Operate Distribution Networks With Safe Deep Reinforcement Learning
IEEE Transactions on Smart Grid, 2022Haibo He, Hepeng Li
exaly +3 more sources
Formal Verification for Safe Deep Reinforcement Learning in Trajectory Generation
2020 Fourth IEEE International Conference on Robotic Computing (IRC), 2020We consider the problem of Safe Deep Reinforcement Learning (DRL) using formal verification in a trajectory generation task. In more detail, we propose an approach to verify whether a trained model can generate trajectories that are guaranteed to meet safety properties (e.g., operate in a limited work-space).
Davide Corsi +3 more
openaire +1 more source
Safe deep reinforcement learning for building energy management
Applied EnergyPeng Wang, Renke Huang, Javier Arroyo
exaly +2 more sources
Verifying Online Safety Properties for Safe Deep Reinforcement Learning
ACM Transactions on Intelligent Systems and TechnologyEnsuring safety in reinforcement learning (RL) is critical for deploying agents in real-world applications. During training, current safe RL approaches often rely on indicator cost functions that provide sparse feedback, resulting in two key limitations: (i) poor sample efficiency due to the lack of safety information in ...
Alessandro Farinelli +2 more
exaly +4 more sources
Safe Deep Reinforcement Learning for Adaptive Cruise Control by Imposing State-Specific Safe Sets
2021 IEEE Intelligent Vehicles Symposium (IV), 2021Deep reinforcement learning has been increasingly discussed for solving continuous control tasks in the field of autonomous driving and driver assistance systems. However, trial-and-error learning and the black-box character of neural networks make it prone to accidental damage in safety-critical environments.
Brosowsky, Mathis +5 more
openaire +2 more sources