Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

TL;DR

This paper introduces a hybrid approach combining Model-Predictive Control and value function approximation via reinforcement learning, improving control performance under model bias and enhancing sample efficiency.

Contribution

It presents a novel framework that integrates MPC with RL by adjusting a parameter to balance model-based and learned value estimates, supported by theoretical analysis and empirical validation.

Findings

Achieves MPC-like performance with biased models

Reduces reliance on accurate models over time

More sample-efficient than pure model-free RL

Abstract

Model-Predictive Control (MPC) is a powerful tool for controlling complex, real-world systems that uses a model to make predictions about future behavior. For each state encountered, MPC solves an online optimization problem to choose a control action that will minimize future cost. This is a surprisingly effective strategy, but real-time performance requirements warrant the use of simple models. If the model is not sufficiently accurate, then the resulting controller can be biased, limiting performance. We present a framework for improving on MPC with model-free reinforcement learning (RL). The key insight is to view MPC as constructing a series of local Q-function approximations. We show that by using a parameter $\lambda$, similar to the trace decay parameter in TD($\lambda$), we can systematically trade-off learned value estimates against the local Q-function approximations. We present a theoretical analysis that shows how error from inaccurate models in MPC and value function estimation in RL can be balanced. We further propose an algorithm that changes $\lambda$ over time to reduce the dependence on MPC as our estimates of the value function improve, and test the efficacy our approach on challenging high-dimensional manipulation tasks with biased models in simulation. We demonstrate that our approach can obtain performance comparable with MPC with access to true dynamics even under severe model bias and is more sample efficient as compared to model-free RL.