Abstract:Automatic programming, the task of generating computer programs compliant with a specification without a human developer, is usually tackled either via genetic programming methods based on mutation and recombination of programs, or via neural language models. We propose a novel method that combines both approaches using a concept of a virtual neuro-genetic programmer: using evolutionary methods as an alternative to gradient descent for neural network training}, or scrum team. We demonstrate its ability to provide performant and explainable solutions for various OpenAI Gym tasks, as well as inject expert knowledge into the otherwise data-driven search for solutions.
| Comments: | Source code is available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) |
| ACM classes: | I.2.2; I.2.6 |
| Cite as: | arXiv:2102.04231 [cs.AI] |
| (or arXiv:2102.04231v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2102.04231 arXiv-issued DOI via DataCite |
Submission history
From: Vadim Liventsev [view email]
[v1]
Mon, 8 Feb 2021 14:26:02 UTC (366 KB)
Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.