ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
This provides a flexible and efficient foundation for researchers, especially those with low compute resources, to work on HPO in reinforcement learning, though it is incremental as it builds on existing datasets and benchmarks.
The authors tackled the problem of costly and time-consuming evaluation of hyperparameter optimization (HPO) methods in reinforcement learning by proposing ARLBench, a benchmark that enables efficient comparisons across diverse HPO approaches, reducing compute requirements to a fraction of previous needs.
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 and large-scale dataset on hyperparameter landscapes that our selection is based on, ARLBench is an efficient, flexible, and future-oriented foundation for research on AutoRL. Both the benchmark and the dataset are available at https://github.com/automl/arlbench.