TR2019-059
Approximate Dynamic Programming For Linear Systems with State and Input Constraints
-
- "Approximate Dynamic Programming For Linear Systems with State and Input Constraints", European Control Conference (ECC), DOI: 10.23919/ECC.2019.8795815, June 2019.BibTeX TR2019-059 PDF
- @inproceedings{Chakrabarty2019jun,
- author = {Chakrabarty, Ankush and Quirynen, Rien and Danielson, Claus and Gao, Weinan},
- title = {Approximate Dynamic Programming For Linear Systems with State and Input Constraints},
- booktitle = {European Control Conference (ECC)},
- year = 2019,
- month = jun,
- doi = {10.23919/ECC.2019.8795815},
- url = {https://www.merl.com/publications/TR2019-059}
- }
,
- "Approximate Dynamic Programming For Linear Systems with State and Input Constraints", European Control Conference (ECC), DOI: 10.23919/ECC.2019.8795815, June 2019.
-
MERL Contact:
-
Research Areas:
Abstract:
Enforcing state and input constraints during reinforcement learning (RL) in continuous state spaces is an open but crucial problem which remains a roadblock to using RL in safetycritical applications. This paper leverages invariant sets to update control policies within an approximate dynamic programming (ADP) framework that guarantees constraint satisfaction for all time and converges to the optimal policy (in a linear quadratic regulator sense) asymptotically. An algorithm for implementing the proposed constrained ADP approach in a data-driven manner is provided. The potential of this formalism is demonstrated via numerical examples.
Related News & Events
-
NEWS Ankush Chakrabarty gave an invited talk on machine learning for constrained control at AI for Engineering in Toronto Date: August 19, 2019 - August 23, 2019
Where: AI for Engineering Summer School 2019
MERL Contact: Ankush Chakrabarty
Research Areas: Artificial Intelligence, Control, Dynamical Systems, Machine LearningBrief- Ankush Chakrabarty, a Visiting Research Scientist in MERL's Control and Dynamical Systems group, gave an invited talk at the AI for Engineering Summer School 2019 hosted by Autodesk. The talk briefly described MERL's research areas, and focused on Dr. Chakrabarty's work at MERL (with collaborators from the CD and DA group) on the use of supervised learning for verification of control systems with simulators/neural nets in the loop, and on constraint-enforcing reinforcement learning. Other speakers at the event included researchers from various academic and industrial research facilities including U Toronto, UW-Seattle, Carnegie Mellon U, the Vector Institute, and the Montreal Institute for Learning Algorithms.
-
NEWS MERL researchers presented more than 8 papers in European Control Conference, ECC 2019 Date: June 25, 2019 - June 28, 2019
Where: Naples, Italy
MERL Contacts: Scott A. Bortoff; Ankush Chakrabarty; Stefano Di Cairano; Devesh K. Jha; Christopher R. Laughman; Daniel N. Nikovski; Diego Romeres; William S. Yerazunis
Research Areas: Control, Machine Learning, OptimizationBrief- The European Control Conference is the premier control conference in Europe. This year MERL was well represented with papers on control for HVAC, machine learning for estimation and control, robot assembly, and optimization methods for control.