mlsanityData to 14 Oct 2026

Gradient-Based Neuroplastic Adaptation for Concurrent Optimization of Neuro-Fuzzy Networks

arXiv 2506.21771 ↗First posted 26 Jun 2025cs.LG cs.NEcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Neuro-fuzzy networks (NFNs) are transparent, symbolic, and universal function approximations that perform as well as conventional neural architectures, but their knowledge is expressed as linguistic IF-THEN rules. Despite these advantages, their systematic design process remains a challenge. Existing work will often sequentially build NFNs by inefficiently isolating parametric and structural identification, leading to a premature commitment to brittle and subpar architecture. We propose a novel application-independent approach called gradient-based neuroplastic adaptation for the concurrent optimization of NFNs' parameters and structure. By recognizing that NFNs' parameters and structure should be optimized simultaneously as they are deeply conjoined, settings previously unapproachable for NFNs are now accessible, such as the online reinforcement learning of NFNs for vision-based tasks. The effectiveness of concurrently optimizing NFNs is empirically shown as it is trained by online reinforcement learning to proficiently play challenging scenarios from a vision-based video game called DOOM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 115 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

18 of 115 references.

References · 18

  1. 2016Layer Normalizationcited by 5,669
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  5. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  8. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  9. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  10. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 341
  11. 2021Mastering Atari Games with Limited Datacited by 237
  12. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 179
6 more
  1. 2019Sparse Sequence-to-Sequence Modelscited by 170
  2. 2022DataPerf: Benchmarks for Data-Centric AI Developmentcited by 90
  3. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  4. 2018ViZDoom Competitions: Playing Doom from Pixelscited by 51
  5. 2016Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policiescited by 19
  6. 2021Curse of Dimensionality for TSK Fuzzy Neural Networks: Explanation and Solutionscited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity
  2. 2025On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization
  3. 2025Noise-based reward-modulated learning
  4. 2024Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
  5. 2026Continual Reinforcement Learning with Neuroevolution
  6. 2026Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics
  7. 2025When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?
  8. 2024Neuroplastic Expansion in Deep Reinforcement Learning