- author = "Jae-Yoon Jung and James A. Reggia",
- title = "Evolving an autonomous agent for non-Markovian reinforcement learning",
- booktitle = "GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computation",
- year = "2009",
- editor = "Guenther Raidl and Franz Rothlauf and Giovanni Squillero and Rolf Drechsler and Thomas Stuetzle and Mauro Birattari and Clare Bates Congdon and Martin Middendorf and Christian Blum and Carlos Cotta and Peter Bosman and Joern Grahl and Joshua Knowles and David Corne and Hans-Georg Beyer and Ken Stanley and Julian F. Miller and Jano {van Hemert} and Tom Lenaerts and Marc Ebner and Jaume Bacardit and Michael O'Neill and Massimiliano {Di Penta} and Benjamin Doerr and Thomas Jansen and Riccardo Poli and Enrique Alba",
- pages = "971--978",
- address = "Montreal",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
- month = "8-12 " # jul,
- organisation = "SigEvo",
- keywords = "genetic algorithms, genetic programming",
- isbn13 = "978-1-60558-325-9",
- bibsource = "DBLP, http://dblp.uni-trier.de",
-
DOI = "
doi:10.1145/1569901.1570034",
- abstract = "In this paper, we investigate the use of nested evolution in which each step of one evolutionary process involves running a second evolutionary process. We apply this approach to build an evolutionary system for reinforcement learning (RL) problems. Genetic programming based on a descriptive encoding is used to evolve the neural architecture, while an evolution strategy is used to evolve the connection weights. We test this method on a non-Markovian RL problem involving an autonomous foraging agent, finding that the evolved networks significantly outperform a rule-based agent serving as a control. We also demonstrate that nested evolution, partitioning into subpopulations, and crossover operations all act synergistically in improving performance in this context.",
-
notes = "GECCO-2009 A joint meeting of the eighteenth
international conference on genetic algorithms
(ICGA-2009) and the fourteenth annual genetic
programming conference (GP-2009).
ACM Order Number 910092.",
