Neurogenetic Programming Framework for Explainable Reinforcement Learning

• URL: http://arxiv.org/abs/2102.04231v1
• Date: Mon, 8 Feb 2021 14:26:02 GMT
• Title: Neurogenetic Programming Framework for Explainable Reinforcement Learning
• Authors: Vadim Liventsev, Aki H\"arm\"a and Milan Petkovi\'c
• Abstract summary: We propose a novel method that combines both approaches using a concept of a virtual neuro-genetic programmer. 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.
• Score: 0.483420384410068
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks [0.0]
  In designing artificial neural networks, one crucial aspect of the innovative approach is suggesting a novel neural architecture. In this work, we use pure Genetic Programming Approach to design CNNs, which employs only one genetic operation. In the course of preliminary experiments, our methodology yields promising results.
  arXiv  Detail & Related papers  (2024-09-30T18:10:06Z)
• Lifelong Reinforcement Learning via Neuromodulation [13.765526492965853]
  Evolution has imbued animals and humans with highly effective adaptive learning functions and decision-making strategies. Central to these theories and integrating evidence from neuroscience into learning is the neuromodulatory system.
  arXiv  Detail & Related papers  (2024-08-15T22:53:35Z)
• Enhancing learning in spiking neural networks through neuronal heterogeneity and neuromodulatory signaling [52.06722364186432]
  We propose a biologically-informed framework for enhancing artificial neural networks (ANNs) Our proposed dual-framework approach highlights the potential of spiking neural networks (SNNs) for emulating diverse spiking behaviors. We outline how the proposed approach integrates brain-inspired compartmental models and task-driven SNNs, bioinspiration and complexity.
  arXiv  Detail & Related papers  (2024-07-05T14:11:28Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks [74.3099028063756]
  We develop a new method with neuronal operations based on lateral connections and Hebbian learning. We show that Hebbian and anti-Hebbian learning on recurrent lateral connections can effectively extract the principal subspace of neural activities. Our method consistently solves for spiking neural networks with nearly zero forgetting.
  arXiv  Detail & Related papers  (2024-02-19T09:29:37Z)
• The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks [59.26515696183751]
  We show that algorithm discovery in neural networks is sometimes more complex. We show that even simple learning problems can admit a surprising diversity of solutions.
  arXiv  Detail & Related papers  (2023-06-30T17:59:13Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)
• Enhancement Programming Skills and Transforming Knowledge of Programming through Neuroeducation Approaches [0.0]
  programming digital devices and developing software is an important professional qualification, which contributes to employment opportunities. Recent development of brain imaging techniques have provided additional opportunity for neuroscientists to explore the functional organization of the human brain. This research is an approach to supporting learning in the field of learning and teaching computer programming.
  arXiv  Detail & Related papers  (2021-05-19T06:26:30Z)
• Functional neural network for decision processing, a racing network of programmable neurons with fuzzy logic where the target operating model relies on the network itself [1.1602089225841632]
  This paper introduces a novel model of artificial intelligence, the functional neural network for modeling human decision-making processes. We believe that this functional neural network has a promising potential to transform the way we can compute decision-making.
  arXiv  Detail & Related papers  (2021-02-24T15:19:35Z)
• BF++: a language for general-purpose program synthesis [0.483420384410068]
  Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models. We propose a new programming language, BF++, designed specifically for automatic programming of agents in a Partially Observable Markov Decision Process setting.
  arXiv  Detail & Related papers  (2021-01-23T19:44:44Z)
• Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs [64.56890245622822]
  Neurocoder is an entirely new class of general-purpose conditional computational machines. It "codes" itself in a data-responsive way by composing relevant programs from a set of shareable, modular programs. We show new capacity to learn modular programs, handle severe pattern shifts and remember old programs as new ones are learnt.
  arXiv  Detail & Related papers  (2020-09-24T01:39:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.