- author = "Mihyar {Al Masalma} and Malcolm Heywood",
- title = "Benchmarking ensemble genetic programming with a linked list external memory on scalable partially observable tasks",
- journal = "Genetic Programming and Evolvable Machines",
- year = "2022",
- volume = "23",
- number = "Suppl 1",
- pages = "s1--s29",
- month = "30 " # nov,
- keywords = "genetic algorithms, genetic programming, External memory, Partial observability, Internal state, Ensembles, noop, pop_head, pop_tail, DIV",
- ISSN = "1389-2576",
-
URL = "
https://rdcu.be/daFLX",
-
DOI = "
doi:10.1007/s10710-022-09446-8",
- size = "29 pages",
- abstract = "Reactive learning agents cannot solve partially observable sequential decision-making tasks as they are limited to defining outcomes purely in terms of the observable state. However, augmenting reactive agents with external memory might provide a path for addressing this limitation. In this work, external memory takes the form of a linked list data structure that programs have to learn how to use. We identify conditions under which additional recurrent connectivity from program output to input is necessary for state disambiguation. Benchmarking against recent results from the neural network literature on three scalable partially observable sequential decision-making tasks demonstrates that the proposed approach scales much more effectively. Indeed, solutions are shown to generalize to far more difficult sequences than those experienced under training conditions. Moreover, recommendations are made regarding the instruction set and additional benchmarking is performed with input state values designed to explicitly disrupt the identification of useful states for later recall. The protected division operator appears to be particularly useful in developing simple solutions to all three tasks.",
-
notes = "See also MSc
https://dalspace.library.dal.ca/handle/10222/81503
http://hdl.handle.net/10222/81503
Faculty of Computer Science, Dalhousie University, 6050 University Avenue, Halifax, NS, Canada",
