Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Le, Bang Giang"'
Autor:
Le, Bang Giang, Ta, Viet Cuong
In this work, we study the problem of finding Pareto optimal policies in multi-agent reinforcement learning problems with cooperative reward structures. We show that any algorithm where each agent only optimizes their reward is subject to suboptimal
Externí odkaz:
http://arxiv.org/abs/2410.19372
Autor:
Le, Bang Giang, Ta, Viet Cuong
Publikováno v:
2022 14th International Conference on Knowledge and Systems Engineering (KSE), Nha Trang, Vietnam, 2022, pp. 1-6
In multi-task reinforcement learning, it is possible to improve the data efficiency of training agents by transferring knowledge from other different but related tasks. Because the experiences from different tasks are usually biased toward the specif
Externí odkaz:
http://arxiv.org/abs/2309.15603