首页|Findings from Academy of Military Sciences Yields New Findings on Intelligent Systems (Embedding Multi-agent Reinforcement Learning Into Behavior Trees With Unexpected Interruptions)
Findings from Academy of Military Sciences Yields New Findings on Intelligent Systems (Embedding Multi-agent Reinforcement Learning Into Behavior Trees With Unexpected Interruptions)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Springer Nature
Investigators discuss new findings in Machine Learning - Intelligent Systems. According to news reporting originating in Beijing, People's Republic of China, by NewsRx journalists, research stated, "Behavior trees have attracted great interest in computer games and robotic applications. However, it lacks the learning ability for dynamic environments." Funders for this research include National Natural Science Foundation of China Youth Science Foundation, National Natural Science Foundation of China Youth Science Foundation. The news reporters obtained a quote from the research from the Academy of Military Sciences, "Previous works combining behavior trees with reinforcement learning either need to construct an independent sub-scenario or train the learning method over the whole game, which is not suited for complex multi-agent games. In this paper, a framework is proposed, named as MARL-BT, that embeds multi-agent reinforcement learning methods into behavior trees. Following the running mechanism of behavior trees, we design the way of collecting samples and the training procedure. Further, we point out a special phenomenon in MARL-BT, i.e., the unexpected interruption, and present an action masking technique to remove its harmful effect on learning performance. Finally, we make extensive experiments on the 11 versus 11 full game in Google Research Football. The introduced MARL-BT framework could get an 11.507% improvement compared to pure BT for certain scenarios."
BeijingPeople's Republic of ChinaAsiaIntelligent SystemsEmerging TechnologiesMachine LearningReinforcement LearningAcademy of Military Sciences
NETL
NSTL
Springer Nature
