Data-driven Rollout for Deterministic Optimal Control
Optimization and Control
2021-09-30 v2 Systems and Control
Systems and Control
Abstract
We consider deterministic infinite horizon optimal control problems with nonnegative stage costs. We draw inspiration from learning model predictive control scheme designed for continuous dynamics and iterative tasks, and propose a rollout algorithm that relies on sampled data generated by some base policy. The proposed algorithm is based on value and policy iteration ideas, and applies to deterministic problems with arbitrary state and control spaces, and arbitrary dynamics. It admits extensions to problems with trajectory constraints, and a multiagent structure.
Cite
@article{arxiv.2105.03116,
title = {Data-driven Rollout for Deterministic Optimal Control},
author = {Yuchao Li and Karl H. Johansson and Jonas Mårtensson and Dimitri P. Bertsekas},
journal= {arXiv preprint arXiv:2105.03116},
year = {2021}
}
Comments
Accepted to CDC 2021