Arlbench: Flexible And Efficient Benchmarking For Hyperparameter Optimization In Reinforcement Learning

Abstract

Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tuning such hyperparameters is both costly and time-consuming. As a result, such approaches are often only evaluated on a single domain or algorithm, making comparisons difficult and limiting insights into their generalizability. We propose ARLBench, a benchmark for hyperparameter optimization (HPO) in RL that allows comparisons of diverse HPO approaches while being highly efficient in evaluation. To enable research into HPO in RL, even in settings with low compute resources, we select a representative subset of HPO tasks spanning a variety of algorithm and environment combinations. This selection allows for generating a performance profile of an automated RL (AutoRL) method using only a fraction of the compute previously necessary, enabling a broader range of researchers to work on HPO in RL. With the extensive

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybecktepe2024arlbench

Related papers

• Sample-efficient Automated Deep Reinforcement Learning (2020)0.00
• Hyperparameter Tuning For Deep Reinforcement Learning Applications (2022)0.00
• Generalized Population-based Training For Hyperparameter Optimization In Reinforcement Learning (2024)9.59
• Automatic Tuning Of Hyper-parameters Of Reinforcement Learning Algorithms Using Bayesian Optimization With Behavioral Cloning (2021)0.00
• Hyperparameter Optimisation With Practical Interpretability And Explanation Methods In Probabilistic Curriculum Learning (2025)0.00
• A Framework For History-aware Hyperparameter Optimisation In Reinforcement Learning (2023)0.00
• ARLO: A Framework For Automated Reinforcement Learning (2022)0.00
• Xrl-bench: A Benchmark For Evaluating And Comparing Explainable Reinforcement Learning Techniques (2024)0.00