机器的重叠的分层学习系统-2014机器人足球世界杯的取胜之道.pdf

In Artificial Intelligence (AIJ), 254:21--43, January 2018. /10.1016/j.artint.2017.09.001 Journal Logo Artificial Intelligence 254 (2018) Overlapping Layered Learning✩ Patrick MacAlpine, Peter Stone Department of Computer Science The University of Texas at Austin Austin, TX 78701, USA {patmac, pstone }@ Abstract Layered learning is a hierarchical machine learning paradigm that enables learning of complex behaviors by incrementally learning a series of sub-behaviors. A key feature of layered learning is that higher layers directly depend on the learned lower layers. In its original formulation, lower layers were frozen prior to learning higher layers. This article considers a major extension to the paradigm that allows learning certain behaviors independently, and then later stitching them together by learning at the “seams” where their influences overlap. The UT Austin Villa 2014 RoboCup 3D simulation team, using such overlapping layered learning, learned a total of 19 layered behaviors for a simulated soccer-playing robot, organized both in series and in parallel. To the best of our knowledge this is more than three times the number of layered behaviors in any prior layered learning system. Furthermore, the complete learning process is repeated on four additional robot body types, showcasing its generality as a paradigm for efficient behavior le