Multi-Fidelity Reinforcement Learning with Gaussian Processes

TL;DR

This paper introduces multi-fidelity reinforcement learning methods using Gaussian Processes to efficiently learn policies with fewer real-world samples, demonstrated through simulations and ground robot experiments.

Contribution

It proposes both model-based and model-free multi-fidelity RL frameworks leveraging Gaussian Processes to reduce sample complexity in real-world environments.

Findings

Up to 40% reduction in samples for model-based RL.

Up to 60% reduction in samples for model-free RL.

Validated through simulations and ground robot navigation experiments.

Abstract

We study the problem of Reinforcement Learning (RL) using as few real-world samples as possible. A naive application of RL can be inefficient in large and continuous state spaces. We present two versions of Multi-Fidelity Reinforcement Learning (MFRL), model-based and model-free, that leverage Gaussian Processes (GPs) to learn the optimal policy in a real-world environment. In the MFRL framework, an agent uses multiple simulators of the real environment to perform actions. With increasing fidelity in a simulator chain, the number of samples used in successively higher simulators can be reduced. By incorporating GPs in the MFRL framework, we empirically observe up to $40\%$ reduction in the number of samples for model-based RL and $60\%$ reduction for the model-free version. We examine the performance of our algorithms through simulations and through real-world experiments for navigation with a ground robot.