← Search

Goran Banjac

2 accepted papers

2021

Accelerating Quadratic Optimization with Reinforcement Learning

NeurIPS 2021poster

First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved. These methods face two persistent challenges: manual hyperparameter tuning and convergence time to high-accur…

2021

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

ICML 2021spotlight

We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations. We assume that the learner is not allowed to interact with the expert and has no access to reinforcement signal of any kind.…

Cited by 12SourcePDFScholar