Neural-Symbolic Integration with Evolvable Policies

• URL: http://arxiv.org/abs/2601.04799v1
• Date: Thu, 08 Jan 2026 10:29:49 GMT
• Title: Neural-Symbolic Integration with Evolvable Policies
• Authors: Marios Thoma, Vassilis Vassiliades, Loizos Michael,
• Abstract summary: Neural-Symbolic (NeSy) Artificial Intelligence has emerged as a promising approach for combining the learning capabilities of neural networks with the interpretable reasoning of symbolic systems.<n>We propose a framework that enables the concurrent learning of both non-differentiable symbolic policies and neural network weights.<n>We demonstrate that NeSy systems starting with empty policies and random neural weights can successfully approximate hidden non-differentiable target policies.
• Score: 2.7324257854160465
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural-Symbolic (NeSy) Artificial Intelligence has emerged as a promising approach for combining the learning capabilities of neural networks with the interpretable reasoning of symbolic systems. However, existing NeSy frameworks typically require either predefined symbolic policies or policies that are differentiable, limiting their applicability when domain expertise is unavailable or when policies are inherently non-differentiable. We propose a framework that addresses this limitation by enabling the concurrent learning of both non-differentiable symbolic policies and neural network weights through an evolutionary process. Our approach casts NeSy systems as organisms in a population that evolve through mutations (both symbolic rule additions and neural weight changes), with fitness-based selection guiding convergence toward hidden target policies. The framework extends the NEUROLOG architecture to make symbolic policies trainable, adapts Valiant's Evolvability framework to the NeSy context, and employs Machine Coaching semantics for mutable symbolic representations. Neural networks are trained through abductive reasoning from the symbolic component, eliminating differentiability requirements. Through extensive experimentation, we demonstrate that NeSy systems starting with empty policies and random neural weights can successfully approximate hidden non-differentiable target policies, achieving median correct performance approaching 100%. This work represents a step toward enabling NeSy research in domains where the acquisition of symbolic knowledge from experts is challenging or infeasible.

Related papers

• Multi-Modal Manipulation via Multi-Modal Policy Consensus [62.49978559936122]
  We propose a new approach to integrate diverse sensory modalities for robotic manipulation.<n>Our method factorizes the policy into a set of diffusion models, each specialized for a single representation.<n>We evaluate our approach on simulated manipulation tasks in RLBench, as well as real-world tasks such as occluded object picking, in-hand spoon reorientation, and puzzle insertion.
  arXiv  Detail & Related papers  (2025-09-27T19:43:04Z)
• Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning [73.18052192964349]
  We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics.<n>By lifting neural parameters to a measure space and modeling training as Wasserstein gradient flow, we show that under geometric constraints, the parameter measure $mu_t$ undergoes two concurrent phenomena.
  arXiv  Detail & Related papers  (2025-06-26T22:40:30Z)
• Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies [51.03989561425833]
  We propose a neuro-symbolic approach called neural DNF-MT for end-to-end policy learning.<n>The differentiable nature of the neural DNF-MT model enables the use of deep actor-critic algorithms for training.<n>We show how the bivalent representations of deterministic policies can be edited and incorporated back into a neural model.
  arXiv  Detail & Related papers  (2025-01-07T15:51:49Z)
• BlendRL: A Framework for Merging Symbolic and Neural Policy Learning [23.854830898003726]
  BlendRL is a neuro-symbolic RL framework that integrates both paradigms within RL agents that use mixtures of both logic and neural policies.<n>We empirically demonstrate that BlendRL agents outperform both neural and symbolic baselines in standard Atari environments.<n>We analyze the interaction between neural and symbolic policies, illustrating how their hybrid use helps agents overcome each other's limitations.
  arXiv  Detail & Related papers  (2024-10-15T15:24:20Z)
• Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients [0.0]
  It has been demonstrated that artificial neural networks like autoencoders or Siamese networks encode meaningful concepts in their latent spaces.<n>We introduce a framework for finding closed-form interpretations of neurons in latent spaces of artificial neural networks.
  arXiv  Detail & Related papers  (2024-09-09T03:26:07Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Simple and Effective Transfer Learning for Neuro-Symbolic Integration [50.592338727912946]
  A potential solution to this issue is Neuro-Symbolic Integration (NeSy), where neural approaches are combined with symbolic reasoning. Most of these methods exploit a neural network to map perceptions to symbols and a logical reasoner to predict the output of the downstream task. They suffer from several issues, including slow convergence, learning difficulties with complex perception tasks, and convergence to local minima. This paper proposes a simple yet effective method to ameliorate these problems.
  arXiv  Detail & Related papers  (2024-02-21T15:51:01Z)
• NeuralFastLAS: Fast Logic-Based Learning from Raw Data [54.938128496934695]
  Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically. Neuro-symbolic approaches overcome this issue by mapping raw data to latent symbolic concepts using a neural network. We introduce NeuralFastLAS, a scalable and fast end-to-end approach that trains a neural network jointly with a symbolic learner.
  arXiv  Detail & Related papers  (2023-10-08T12:33:42Z)
• Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction [23.552659248243806]
  We introduce Neurally gUided Differentiable loGic policiEs (NUDGE) NUDGE exploits trained neural network-based agents to guide the search of candidate-weighted logic rules, then uses differentiable logic to train the logic agents. Our experimental evaluation demonstrates that NUDGE agents can induce interpretable and explainable policies while outperforming purely neural ones and showing good flexibility to environments of different initial states and problem sizes.
  arXiv  Detail & Related papers  (2023-06-02T10:59:44Z)
• Extensions to Generalized Annotated Logic and an Equivalent Neural Architecture [4.855957436171202]
  We propose a list of desirable criteria for neuro symbolic systems and examine how some of the existing approaches address these criteria. We then propose an extension to annotated generalized logic that allows for the creation of an equivalent neural architecture. Unlike previous approaches that rely on continuous optimization for the training process, our framework is designed as a binarized neural network that uses discrete optimization.
  arXiv  Detail & Related papers  (2023-02-23T17:39:46Z)
• Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces [20.260546238369205]
  We propose a framework that combines the pattern recognition abilities of neural networks with symbolic reasoning and background knowledge. We take inspiration from the 'neural algorithmic reasoning' approach [DeepMind 2020] and use problem-specific background knowledge. We test this on visual analogy problems in RAVENs Progressive Matrices, and achieve accuracy competitive with human performance.
  arXiv  Detail & Related papers  (2022-09-19T04:03:20Z)

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.