Summary of Arlbench: Flexible and Efficient Benchmarking For Hyperparameter Optimization in Reinforcement Learning, by Jannis Becktepe et al.
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
by Jannis Becktepe, Julian Dierkes, Carolin Benjamins, Aditya Mohan, David Salinas, Raghu Rajan, Frank Hutter, Holger Hoos, Marius Lindauer, Theresa Eimer
First submitted to arxiv on: 27 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed ARLBench is a benchmark for hyperparameter optimization in reinforcement learning (RL) that enables comparisons of diverse approaches while being efficient in evaluation. It selects a representative subset of HPO tasks spanning various algorithm and environment combinations, allowing researchers to work on HPO in RL with limited compute resources. The benchmark and dataset are available at this GitHub URL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes ARLBench, a new way to test how well automated reinforcement learning (RL) works by comparing different approaches to choosing the right hyperparameters. This can be done efficiently, making it possible for more researchers to work on RL even with limited computer power. The benchmark and dataset are available online. |
Keywords
» Artificial intelligence » Hyperparameter » Optimization » Reinforcement learning
