Model-based Policy Search for Partially Measurable Systems
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.
Cite
@article{arxiv.2101.08740,
title = {Model-based Policy Search for Partially Measurable Systems},
author = {Fabio Amadio and Alberto Dalla Libera and Ruggero Carli and Daniel Nikovski and Diego Romeres},
journal= {arXiv preprint arXiv:2101.08740},
year = {2021}
}
Comments
Accepted to 3rd Robot Learning Workshop: Grounding Machine Learning Development in the Real World (NeurIPS 2020)