Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives

TL;DR

This paper introduces a model selection framework that adaptively chooses learning rates in reinforcement learning, enabling learning rate-free algorithms that perform well even with non-stationary objectives.

Contribution

It proposes a novel, generic model selection approach for RL that dynamically tunes learning rates without prior knowledge, improving robustness to non-stationary environments.

Findings

Data-driven model selection outperforms standard bandit algorithms in non-stationary settings.

The framework is compatible with any RL algorithm and does not depend on specific optimizers.

Adaptive learning rate tuning enhances RL performance and convergence in challenging scenarios.

Abstract

The performance of reinforcement learning (RL) algorithms is sensitive to the choice of hyperparameters, with the learning rate being particularly influential. RL algorithms fail to reach convergence or demand an extensive number of samples when the learning rate is not optimally set. In this work, we show that model selection can help to improve the failure modes of RL that are due to suboptimal choices of learning rate. We present a model selection framework for Learning Rate-Free Reinforcement Learning that employs model selection methods to select the optimal learning rate on the fly. This approach of adaptive learning rate tuning neither depends on the underlying RL algorithm nor the optimizer and solely uses the reward feedback to select the learning rate; hence, the framework can input any RL algorithm and produce a learning rate-free version of it. We conduct experiments for policy optimization methods and evaluate various model selection strategies within our framework. Our results indicate that data-driven model selection algorithms are better alternatives to standard bandit algorithms when the optimal choice of hyperparameter is time-dependent and non-stationary.