Neurogenetic Programming Framework for Explainable Reinforcement Learning
This work addresses the problem of generating explainable and performant solutions for reinforcement learning tasks, which is important for researchers and practitioners seeking transparent AI systems.
This paper proposes a novel neurogenetic programming framework that combines evolutionary methods with neural language models to automatically generate computer programs. The framework is demonstrated to provide performant and explainable solutions for various OpenAI Gym tasks, and can also incorporate expert knowledge.
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.