TY - GEN
T1 - Data-driven Rollout for Deterministic Optimal Control
AU - Li, Yuchao
AU - Johansson, Karl H.
AU - Martensson, Jonas
AU - Bertsekas, DImitri P.
N1 - Funding Information:
This work was supported by the Swedish Foundation for Strategic Research, the Swedish Research Council, and the Knut and Alice Wallenberg Foundation.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85126000020&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126000020&partnerID=8YFLogxK
U2 - 10.1109/CDC45484.2021.9683499
DO - 10.1109/CDC45484.2021.9683499
M3 - Conference contribution
AN - SCOPUS:85126000020
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 2169
EP - 2176
BT - 60th IEEE Conference on Decision and Control, CDC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 60th IEEE Conference on Decision and Control, CDC 2021
Y2 - 13 December 2021 through 17 December 2021
ER -