Model-based Policy Search for Partially Measurable Systems
| Autor: | Amadio, Fabio, Libera, Alberto Dalla, Carli, Ruggero, Nikovski, Daniel, Romeres, Diego |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Robotics Computer Science - Machine Learning Reinforcement learning FOS: Electrical engineering electronic engineering information engineering Gaussian processes Systems and Control (eess.SY) System identification Electrical Engineering and Systems Science - Systems and Control Robotics (cs.RO) Reinforcement learning Gaussian processes System identification Machine Learning (cs.LG) |
| DOI: | 10.48550/arxiv.2101.08740 |
| Popis: | 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. Comment: Accepted to 3rd Robot Learning Workshop: Grounding Machine Learning Development in the Real World (NeurIPS 2020) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|