-
Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization
Model-based reinforcement learning algorithms tend to achieve higher sam...
read it
-
Deep Residual Reinforcement Learning
We revisit residual algorithms in both model-free and model-based reinfo...
read it
-
Probabilistic Programming Bots in Intuitive Physics Game Play
Recent findings suggest that humans deploy cognitive mechanism of physic...
read it
-
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
We present CURL: Contrastive Unsupervised Representations for Reinforcem...
read it
-
A novel control mode of bionic morphing tail based on deep reinforcement learning
In the field of fixed wing aircraft, many morphing technologies have bee...
read it
-
MOFA: Modular Factorial Design for Hyperparameter Optimization
Automated hyperparameter optimization (HPO) has shown great power in man...
read it
-
Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction
Model-free reinforcement learning based methods such as Proximal Policy ...
read it
Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL
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 https://github.com/MathPhysSim/FERMI_RL_Paper.
READ FULL TEXT
Comments
There are no comments yet.