Model based reinforcement learning implemenation of ME-TRPO on a physical simulation od AWAKE

Advanced control & optimisation techniques for the AWAKE electron line – implementing classical and data-driven algorithms for rapid, efficient beam steering under delayed and uncertain conditions.

Classical reinforcement learning example from Sutton and Barto

The repo for the FERMI FEL paper using model-based and model-free reinforcement learning methods to solve a particle accelerator operation problem.

Welcome to our PINNs_LNNs_HNNs repository—an open space for sharing ideas, insights, and experiments related to Physics-Informed Neural Networks (PINNs), Lagrangian Neural Networks (LNNs), and Hami…

Config files for my GitHub profile.

An implementation of the Normalized Advantage Function Reinforcement Learning Algorithm with Prioritized Experience Replay

Additional material for the lecture and excercises

Optimizing decision-making for OceanHarvest's abalone harvesting. This project uses statistical modeling, neural networks, forecasting, Dynamic Programming and Markov Decision Process (MDP) to make…