RSSAmplifier

Vadim Liventsev · Feb 8, 2021

Neurogenetic Programming Framework for Explainable Reinforcement Learning

0
Sign in to vote or save

[Submitted on 8 Feb 2021] · arXiv.org

View PDF HTML (experimental)

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)

Read the original on vadim.me

Comments

Nothing yet. Say the first thing.

    Sign in to join the conversation.