Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials
在DARPA的AlphaDogfight试验中用于空战的分层强化学习
机构 * Primordial Labs ; Lockheed Martin Artificial Intelligence Center, Applied AI Team(洛克希德·马丁人工智能中心,应用人工智能团队) ; United States Air Force(美国空军)
专题命中 模仿学习与强化学习 :robotics(abstract);分类 cs.LG
AI总结 针对高维连续控制难题,在DARPA的AlphaDogfight试验中,采用由高级策略选择器和低级策略组成的分层深度强化学习方法,整合专家知识训练,超越人类专家飞行员,获ADT锦标赛第二名。
Comments 15 pages (main text) + 4 pages (supplementary material), 13 figures. This work has been accepted for publication in IEEE Transactions on Artificial Intelligence (IEEE-TAI). This replaces the previous conference-version presented at the 2021 International Conference on Unmanned Aircraft System (ICUAS 21), June 15-18, 2021, Athens, Greece
Journal ref IEEE Transactions on Artificial Intelligence (IEEE-TAI), vol. 4, no. 6, pp. 1371-1385, 2023