Výsledky vyhledávání - "Yi Hsiang Chang"

Reusability and Transferability of Macro Actions for Reinforcement Learning

Autor: Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

Publikováno v: ACM Transactions on Evolutionary Learning and Optimization. 2:1-16

Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an RL agent is able to bypass intermediate states to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70fdc3df7a0404ff11ea9f3765332ad4
https://doi.org/10.1145/3514260

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání