Reinforcement learning for selective key applications in power systems: Recent advances and future challenges

X Chen, G Qu, Y Tang, S Low… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
With large-scale integration of renewable generation and distributed energy resources,
modern power systems are confronted with new operational challenges, such as growing …

Exploiting linear models for model-free nonlinear control: A provably convergent policy gradient approach

G Qu, C Yu, S Low, A Wierman - 2021 60th IEEE Conference …, 2021 - ieeexplore.ieee.org
Model-free learning-based control methods have seen great success recently. However,
such methods typically suffer from poor sample complexity and limited convergence …

Model-based reinforcement learning with multi-step plan value estimation

H Lin, Y Sun, J Zhang, Y Yu - ECAI 2023, 2023 - ebooks.iospress.nl
A promising way to improve the sample efficiency of reinforcement learning is model-based
methods, in which many explorations and evaluations can happen in the learned models to …

Applications of the free energy principle to machine learning and neuroscience

B Millidge - arxiv preprint arxiv:2107.00140, 2021 - arxiv.org
In this PhD thesis, we explore and apply methods inspired by the free energy principle to two
important areas in machine learning and neuroscience. The free energy principle is a …

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning

H Lin, YY Xu, Y Sun, Z Zhang, YC Li, C Jia, J Ye… - arxiv preprint arxiv …, 2024 - arxiv.org
Model-based methods in reinforcement learning offer a promising approach to enhance
data efficiency by facilitating policy exploration within a dynamics model. However …

Role of reinforcement learning for risk‐based robust control of cyber‐physical energy systems

Y Du, S Chatterjee, A Bhattacharya, A Dutta… - Risk …, 2023 - Wiley Online Library
Critical infrastructures such as cyber‐physical energy systems (CPS‐E) integrate information
flow and physical operations that are vulnerable to natural and targeted failures. Safe …