TR2019-059

Approximate Dynamic Programming For Linear Systems with State and Input Constraints


    •  Chakrabarty, A., Quirynen, R., Danielson, C., Gao, W., "Approximate Dynamic Programming For Linear Systems with State and Input Constraints", European Control Conference (ECC), June 2019.
      BibTeX Download 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,
      • url = {https://www.merl.com/publications/TR2019-059}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Machine Learning


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.