2024-10-09-shala24a.md

title	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
HPO-RL-Bench: A Zero-Cost Benchmark for HPO in Reinforcement Learning	MlB61zPAeR	Despite the undeniable importance of optimizing the hyperparameters of RL algorithms, existing state-of-the-art Hyperparameter Optimization (HPO) techniques are not frequently utilized by RL researchers. To catalyze HPO research in RL, we present a new large-scale benchmark that includes pre-computed reward curve evaluations of hyperparameter configurations for six established RL algorithms (PPO, DDPG, A2C, SAC, TD3, DQN) on 22 environments (Atari, Mujoco, Control), repeated for multiple seeds. We exhaustively computed the reward curves of all possible combinations of hyperparameters for the considered hyperparameter spaces for each RL algorithm in each environment. As a result, our benchmark permits zero-cost experiments for deploying and comparing new HPO methods. In addition, the benchmark offers a set of integrated HPO methods, enabling plug-and-play tuning of the hyperparameters of new RL algorithms, while pre-computed evaluations allow a zero-cost comparison of a new RL algorithm against the tuned RL baselines in our benchmark.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	shala24a	0	HPO-RL-Bench: A Zero-Cost Benchmark for HPO in Reinforcement Learning	18/1	31	18/1-31	18	false	Shala, Gresa and Arango, Sebastian Pineda and Biedenkapp, Andr\'e and Hutter, Frank and Grabocka, Josif	given family Gresa Shala given family Sebastian Pineda Arango given family André Biedenkapp given family Frank Hutter given family Josif Grabocka	2024-10-09		Proceedings of the Third International Conference on Automated Machine Learning	256	inproceedings	date-parts 2024 10 9	https://raw.githubusercontent.com/mlresearch/v256/main/assets/shala24a/shala24a.pdf