Neurogenetic Programming Framework for Explainable Reinforcement Learning
| Autor: | Vadim Liventsev, Milan Petkovic, Aki Härmä |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence Genetic programming computer.software_genre 01 natural sciences Machine Learning (cs.LG) Scrum 03 medical and health sciences 0302 clinical medicine Reinforcement learning Neural and Evolutionary Computing (cs.NE) 0101 mathematics Programmer I.2.2 business.industry Programming language I.2.6 010102 general mathematics Computer Science - Neural and Evolutionary Computing Software framework Artificial Intelligence (cs.AI) Mutation (genetic algorithm) Automatic programming business computer 030217 neurology & neurosurgery Program synthesis |
| Zdroj: | GECCO Companion |
| Popis: | 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. Source code is available at https://github.com/vadim0x60/cibi |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|