Information Theoretic Model Predictive Q-Learning

TL;DR

This paper introduces a new Q-learning algorithm that combines information theoretic MPC with entropy regularized RL, enabling effective learning with biased models and improving control in complex environments.

Contribution

It establishes a theoretical link between information theoretic MPC and entropy regularized RL, and develops a Q-learning method that leverages biased models for better control.

Findings

Demonstrates improved control performance over traditional methods in simulation tasks.

Validates the approach's ability to handle biased models effectively.

Shows potential for systematic deployment of RL in real-world systems.

Abstract

Model-free Reinforcement Learning (RL) works well when experience can be collected cheaply and model-based RL is effective when system dynamics can be modeled accurately. However, both assumptions can be violated in real world problems such as robotics, where querying the system can be expensive and real-world dynamics can be difficult to model. In contrast to RL, Model Predictive Control (MPC) algorithms use a simulator to optimize a simple policy class online, constructing a closed-loop controller that can effectively contend with real-world dynamics. MPC performance is usually limited by factors such as model bias and the limited horizon of optimization. In this work, we present a novel theoretical connection between information theoretic MPC and entropy regularized RL and develop a Q-learning algorithm that can leverage biased models. We validate the proposed algorithm on sim-to-sim control tasks to demonstrate the improvements over optimal control and reinforcement learning from scratch. Our approach paves the way for deploying reinforcement learning algorithms on real systems in a systematic manner.