Learning Rate-free Reinforcement Learning: A Case For Model Selection With Non-stationary Objectives

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 re

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyafshar2024learning

Related papers

• Improved Training Mechanism For Reinforcement Learning Via Online Model Selection (2025)0.00
• Online Model Selection For Reinforcement Learning With Function Approximation (2020)0.00
• Model-agnostic Solutions For Deep Reinforcement Learning In Non-ergodic Contexts (2026)0.00
• Simplifying Model-based RL: Learning Representations, Latent-space Models, And Policies With One Objective (2022)0.00
• Dynamic Learning Rate For Deep Reinforcement Learning: A Bandit Approach (2024)0.00
• Oracle Inequalities For Model Selection In Offline Reinforcement Learning (2022)0.00
• Algorithmic Framework For Model-based Deep Reinforcement Learning With Theoretical Guarantees (2018)0.00
• A Framework For History-aware Hyperparameter Optimisation In Reinforcement Learning (2023)0.00