Layered Learning
Layered Learning is a hierarchical machine learning paradigm designed for domains that are too complex to learn straight from inputs to outputs. It relies on a given subtask decomposition. Learning in each layer directly enables learning at the next higher up layer in a variety of possible ways. Layered Learning was the topic of Peter Stone's Ph.D. thesis.
People
Peter Stone Faculty pstone [at] cs utexas edu
Publications
Overlapping Layered Learning 2018
Patrick MacAlpine and Peter Stone, Artificial Intelligence, Vol. 254 (2018), pp. 21--43. Elsevier.
A Study of Layered Learning Strategies Applied to Individual Behaviors in Robot Soccer 2016
David L. Leottau, Javier Ruiz-del-Solar, Patrick MacAlpine, and Peter Stone, In {R}obo{C}up-2015: Robot Soccer World Cup {XIX}, Luis Almeida and Jianmin Ji and Gerald Steinbauer and Sean Luke (Eds.), Berlin, Germany 2016. Springer Verlag.
UT Austin Villa 2014: RoboCup 3D Simulation League Champion via Overlapping Layered Learning 2015
Patrick MacAlpine, Mike Depinet, and Peter Stone, In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), January 2015.
Evolving Keepaway Soccer Players through Task Decomposition 2005
Shimon Whiteson, Nate Kohl, Risto Miikkulainen, and Peter Stone, Machine Learning, Vol. 59, 1 (2005), pp. 5-30.
Concurrent Layered Learning 2003
Shimon Whiteson and Peter Stone, In {AAMAS} 2003: {P}roceedings of the Second International Joint Conference on Autonomous Agents and Multi-Agent Systems, Jeffrey S. Rosenschein and Tuomas Sandholm and Michael Wooldridge and...
Layered Learning 2000
Peter Stone and Manuela Veloso, In Machine Learning: ECML 2000 (Proceedings of the Eleventh European Conference on Machine Learning), Ramon Lopez de Mantaras and Enric Plaza (Eds.), pp. 369-381, Barcelona,Catalonia,Spain, May...
A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server 1998
Peter Stone and Manuela Veloso, Applied Artificial Intelligence, Vol. 12 (1998), pp. 165-188.
Labs
Learning Agents