The combination of model predictive control (MPC) and learning methods has been gaining increasing attention as a tool to control systems that may be difficult to model. Using MPC as a function approximator in reinforcement learning (RL) is one approach to reduce the reliance on accurate models. RL is dependent on exploration to learn, and currently, simple heuristics based on random perturbations are most common. This paper considers variance-based exploration in RL geared towards using MPC as function approximator. We propose to use a non-probabilistic measure of uncertainty of the value function approximator in value-based RL methods. Uncertainty is measured by a variance estimate based on inverse distance weighting (IDW). The IDW framework is computationally cheap to evaluate and therefore well-suited in an online setting, using already sampled state transitions and rewards. The gradient of the variance estimate is then used to perturb the policy parameters in a direction where the variance of the value function estimate is increasing. The proposed method is verified on two simulation examples, considering both linear and nonlinear system dynamics, and compared to standard exploration methods using random perturbations. © 2013 IEEE.

Variance-Based Exploration for Learning Model Predictive Control

A. Bemporad;
2023-01-01

Abstract

The combination of model predictive control (MPC) and learning methods has been gaining increasing attention as a tool to control systems that may be difficult to model. Using MPC as a function approximator in reinforcement learning (RL) is one approach to reduce the reliance on accurate models. RL is dependent on exploration to learn, and currently, simple heuristics based on random perturbations are most common. This paper considers variance-based exploration in RL geared towards using MPC as function approximator. We propose to use a non-probabilistic measure of uncertainty of the value function approximator in value-based RL methods. Uncertainty is measured by a variance estimate based on inverse distance weighting (IDW). The IDW framework is computationally cheap to evaluate and therefore well-suited in an online setting, using already sampled state transitions and rewards. The gradient of the variance estimate is then used to perturb the policy parameters in a direction where the variance of the value function estimate is increasing. The proposed method is verified on two simulation examples, considering both linear and nonlinear system dynamics, and compared to standard exploration methods using random perturbations. © 2013 IEEE.
2023
Model-predictive control
Q-learning
Inverse distance weighting
Reinforcement learning
File in questo prodotto:
File Dimensione Formato  
Variance-Based_Exploration_for_Learning_Model_Predictive_Control.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 1.85 MB
Formato Adobe PDF
1.85 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11771/27858
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
social impact