Differential Reinforcement Learning outperforms Multi-objective TD3, Multi-Objective Bayesian Optimization, Multi-objective Genetic Algorithms on highly complex constrained …
By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment. In addition, …
Invited Talk Current progress on machine learning applications for particle accelerators and its scope for Fusion Science.
Invited Talk Application of Machine Learning to improve accelerator operation, application of conditional models to predict anomalies at SNS accelerator.
Scientific Optimization Control Toolkit (SOCT) is an open-source Python framework built on OpenAI Gymnasium for designing and deploying reinforcement learning agents for scientific …