2021/10/08 by Vladislav Kurenkov, Kurenkov, Vladislav, С. В. Колесников +2 · 1 citation
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Mobile Crowdsensing and Crowdsourcing #Reinforcement Learning in Robotics #Smart Grid Energy Management
paper · pdf · doi:10.48550/arxiv.2110.04156
openalex publication_date 2021/10/08 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
In this work, we argue for the importance of an online evaluation budget for a reliable comparison of deep offline RL algorithms. First, we delineate that the online evaluation budget is problem-dependent, where some problems allow for less but others for more. And second, we demonstrate that the preference between algorithms is budget-dependent across a diverse range of decision-making domains such as Robotics, Finance, and Energy Management. Following the points above, we suggest reporting the performance of deep offline RL algorithms under varying online evaluation budgets. To facilitate this, we propose to use a reporting tool from the NLP field, Expected Validation Performance. This technique makes it possible to reliably estimate expected maximum performance under different budgets while not requiring any additional computation beyond hyperparameter search. By employing this tool, we also show that Behavioral Cloning is often more favorable to offline RL algorithms when working within a limited budget.