Bigger, Better, Faster: Human-level Atari with human-level efficiency

Autor:	Schwarzer, Max, Obando-Ceron, Johan, Courville, Aaron, Bellemare, Marc, Agarwal, Rishabh, Castro, Pablo Samuel
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	We introduce a value-based RL agent, which we call BBF, that achieves super-human performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used for value estimation, as well as a number of other design choices that enable this scaling in a sample-efficient manner. We conduct extensive analyses of these design choices and provide insights for future work. We end with a discussion about updating the goalposts for sample-efficient RL research on the ALE. We make our code and data publicly available at https://github.com/google-research/google-research/tree/master/bigger_better_faster. Comment: ICML 2023, revised version
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.19452 Zobrazit plný text záznamu View this record from Arxiv