# Safe Reinforcement Learning Using Robust MPC

## TL;DR

This paper proposes a method combining Reinforcement Learning and Model Predictive Control to achieve safe, stable, and near-optimal control in uncertain systems, addressing safety concerns often overlooked in RL.

## Contribution

It introduces a novel integration of RL with MPC to enhance safety and stability while maintaining optimality in control tasks.

## Key findings

- The combined RL-MPC controller ensures safety and stability in uncertain environments.
- Simulation results demonstrate improved safety guarantees over standard RL methods.
- The approach balances optimality and robustness in control performance.

## Abstract

Reinforcement Learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well-established, many critical aspects still need to be tackled, including safety and stability issues. These issues, while partially neglected by the RL community, are central to the control community which has been widely investigating them. Model Predictive Control (MPC) is one of the most successful control techniques because, among others, of its ability to provide such guarantees even for uncertain constrained systems. Since MPC is an optimization-based technique, optimality has also often been claimed. Unfortunately, the performance of MPC is highly dependent on the accuracy of the model used for predictions. In this paper, we propose to combine RL and MPC in order to exploit the advantages of both and, therefore, obtain a controller which is optimal and safe. We illustrate the results with a numerical example in simulations.