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 Contact:
  • 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

    •  NEWS    Diego Romeres gave an invited talk at the Autonomy Talks at ETH, Zurich.
      Date: February 15, 2021
      Where: Virtual
      Research Areas: Artificial Intelligence, Machine Learning, Robotics
      Brief
      • Diego Romeres, a Principal Research Scientist in MERL's Data Analytics group, gave the invited talk "Reinforcement Learning for Robotics" at the Autonomy Talks organized at ETH, Zurich. In the presentation, some directions to apply Model-based Reinforcement Learning algorithms to real-world applications are presented together with a novel MBRL algorithm called MC-PILCO. The link to the presentation is https://www.youtube.com/watch?v=wYgbgMa4j-s.
    •  

  • 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}
    • }