DeepAI AI Chat
Log In Sign Up

Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL

by   Simon Hirlaender, et al.

Reinforcement learning holds tremendous promise in accelerator controls. The primary goal of this paper is to show how this approach can be utilised on an operational level on accelerator physics problems. Despite the success of model-free reinforcement learning in several domains, sample-efficiency still is a bottle-neck, which might be encompassed by model-based methods. We compare well-suited purely model-based to model-free reinforcement learning applied to the intensity optimisation on the FERMI FEL system. We find that the model-based approach demonstrates higher representational power and sample-efficiency, while the asymptotic performance of the model-free method is slightly superior. The model-based algorithm is implemented in a DYNA-style using an uncertainty aware model, and the model-free algorithm is based on tailored deep Q-learning. In both cases, the algorithms were implemented in a way, which presents increased noise robustness as omnipresent in accelerator control problems. Code is released in


Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

Model-based reinforcement learning algorithms tend to achieve higher sam...

Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control

Model-based reinforcement learning (MBRL) is believed to have much highe...

Deep Residual Reinforcement Learning

We revisit residual algorithms in both model-free and model-based reinfo...

Probabilistic Programming Bots in Intuitive Physics Game Play

Recent findings suggest that humans deploy cognitive mechanism of physic...

Optimising Stochastic Routing for Taxi Fleets with Model Enhanced Reinforcement Learning

The future of mobility-as-a-Service (Maas)should embrace an integrated s...

MOFA: Modular Factorial Design for Hyperparameter Optimization

Automated hyperparameter optimization (HPO) has shown great power in man...

Hint assisted reinforcement learning: an application in radio astronomy

Model based reinforcement learning has proven to be more sample efficien...