TR2020-174

Model-based Policy Search for Partially Measurable Systems

    •  Romeres, D., Amadio, F., Dalla Libera, A., Nikovski, D.N., Carli, R., "Model-based Policy Search for Partially Measurable Systems", Advances in Neural Information Processing Systems (NeurIPS), December 2020.
      BibTeX TR2020-174 PDF
      • @inproceedings{Romeres2020dec2,
      • author = {Romeres, Diego and Amadio, Fabio and Dalla Libera, Alberto and Nikovski, Daniel N. and Carli, Ruggero},
      • title = {Model-based Policy Search for Partially Measurable Systems},
      • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
      • year = 2020,
      • month = dec,
      • url = {https://www.merl.com/publications/TR2020-174}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Machine Learning, Robotics

Abstract:

In this paper, we propose a Model-Based Reinforcement Learning (MBRL) algorithm for Partially Measurable Systems (PMS), i.e., systems where the state can not be directly measured, but must be estimated through proper state observers. The proposed algorithm, named Monte Carlo Probabilistic Inference for Learning Control for Partially Measurable Systems (MC-PILCO4PMS), relies on Gaussian Processes (GPs) to model the system dynamics, and on a Monte Carlo approach to update the policy parameters. W.r.t. previous GP-based MBRL algorithms, MC-PILCO4PMS models explicitly the presence of state observers during policy optimization, allowing to deal PMS. The effectiveness of the proposed algorithm has been tested both in simulation and in two real systems

 

  • Related News & Events

  • Related Publication

  •  Romeres, D., Amadio, F., Dalla Libera, A., Nikovski, D.N., Carli, R., "Model-based Policy Search for Partially Measurable Systems", arXiv, January 2021.
    BibTeX arXiv
    • @article{Romeres2021jan,
    • author = {Romeres, Diego and Amadio, Fabio and Dalla Libera, Alberto and Nikovski, Daniel N. and Carli, Ruggero},
    • title = {Model-based Policy Search for Partially Measurable Systems},
    • journal = {arXiv},
    • year = 2021,
    • month = jan,
    • url = {https://arxiv.org/abs/2101.08740}
    • }