# Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments

arXiv: https://arxiv.org/abs/2109.07120 · HTML: https://mlsanity.com/paper/2109.07120/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2021.

## Built on by (most cited first, 5 of 5)

- [Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control](https://mlsanity.com/paper/2210.01525/) (2022)
- [On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR](https://mlsanity.com/paper/2312.05465/) (2023)
- [Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making](https://mlsanity.com/paper/2512.17091/) (2025)
- [MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins](https://mlsanity.com/paper/2606.26392/) (2026)
- [RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC](https://mlsanity.com/paper/2604.27450/) (2026)

## Abstract (arXiv)

The successful operation of mobile robots requires them to adapt rapidly to environmental changes. To develop an adaptive decision-making tool for mobile robots, we propose a novel algorithm that combines meta-reinforcement learning (meta-RL) with model predictive control (MPC). Our method employs an off-policy meta-RL algorithm as a baseline to train a policy using transition samples generated by MPC when the robot detects certain events that can be effectively handled by MPC, with its explicit use of robot dynamics. The key idea of our method is to switch between the meta-learned policy and the MPC controller in a randomized and event-triggered fashion to make up for suboptimal MPC actions caused by the limited prediction horizon. During meta-testing, the MPC module is deactivated to significantly reduce computation time in motion control. We further propose an online adaptation scheme that enables the robot to infer and adapt to a new task within a single trajectory. The performance of our method has been demonstrated through simulations using a nonlinear car-like vehicle model with (i) synthetic movements of obstacles, and (ii) real-world pedestrian motion data. The simulation results indicate that our method outperforms other algorithms in terms of learning efficiency and navigation quality.