影响力指数

-/100

发表论文1 篇

平均评分4.0

年均产出1.0 篇/年

Hesong Huang

Postdoc@National University of Defense Technology·中国·OpenReview

研究方向

Cognitive Behavior Modeling · Intelligent Air Combat · Deep Reinforcement Learning

One Policy Learns Them All: Synergizing Prior-Guided Exploitation and Online Exploration in Curriculum Based MARL

ICLR 2026Rejected

合作者 (6)