Genetic programming with external memory in sequence recall tasks
Mihyar Al Masalma, Malcolm Iain Heywood · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2022
Partially observable tasks imply that a learning agent has to recall previous state in order to make a decision in the present. Recent research with neural networks have investigated both internal and external memory mechanisms for this purpose, as well as proposing benchmarks to measure their effectiveness. These developments motivate our investigation using genetic programming and an external linked list memory model. A thorough empirical evaluation using a scalable sequence recall benchmark establishes the underlying strength of the approach. In addition, we assess the impact of decisions made regarding the instruction set and characterize the sensitivity to noise / obfuscation in the definition of the benchmarks. Compared to neural solutions to these benchmarks, GP extends the state-of-the-art to greater task depths than previously possible.