notesum.ai

Published at October 23

cs.CG

Released Date: October 23, 2024

Authors: Nguyen Van Huynh¹, Bolun Zhang¹, Dinh-Hieu Tran¹, Dinh Thai Hoang¹, Diep N. Nguyen¹, Gan Zheng¹, Dusit Niyato¹, Quoc-Viet Pham¹

Aff.: ¹Not specified

Given state

s_{t}

, performing action

a_{t}

based on the current policy and observe immediate reward

r_{t}

and next state

s_{t+1}