Reinforcement learning based robust control algorithms for coherent pulse stacking
A Abuduweili, J Wang, B Yang, A Wang, Z Zhang - Optics Express, 2021 - opg.optica.org
For the fast and robust control of the delay lines for coherent pulse stacking, we combined
the stochastic parallel gradient descent with momentum (SPGDM) and the soft actor-critic …
the stochastic parallel gradient descent with momentum (SPGDM) and the soft actor-critic …
An Optical Controlling Environment and Reinforcement Learning Benchmarks
A Abuduweili, C Liu - arXiv preprint arXiv:2203.12114, 2022 - arxiv.org
Deep reinforcement learning has the potential to address various scientific problems. In this
paper, we implement an optics simulation environment for reinforcement learning based …
paper, we implement an optics simulation environment for reinforcement learning based …