mlsanityData to 14 Oct 2026

Discovering Continuous-Time Memory-Based Symbolic Policies using Genetic Programming

arXiv 2406.02765 ↗First posted 4 Jun 2024cs.NE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence techniques are increasingly being applied to solve control problems, but often rely on black-box methods without transparent output generation. To improve the interpretability and transparency in control systems, models can be defined as white-box symbolic policies described by mathematical expressions. For better performance in partially observable and volatile environments, the symbolic policies are extended with memory represented by continuous-time latent variables, governed by differential equations. Genetic programming is used for optimisation, resulting in interpretable policies consisting of symbolic expressions. Our results show that symbolic policies with memory compare with black-box policies on a variety of control tasks. Furthermore, the benefit of the memory in symbolic policies is demonstrated on experiments where memory-less policies fall short. Overall, we present a method for evolving high-performing symbolic policies that offer interpretability and transparency, which lacks in black-box models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 83 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

23 of 83 references.

References · 23

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2020Knowledge Distillation: A Surveycited by 1,603
  4. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  5. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  6. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  7. 2020A Survey on Neural Network Interpretabilitycited by 291
  8. 2022On Neural Differential Equationscited by 268
  9. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  10. 2020Explainable Reinforcement Learning: A Surveycited by 141
  11. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  12. 2015Memory-based control with recurrent neural networkscited by 78
11 more
  1. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  2. 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 48
  3. 2022Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systemscited by 35
  4. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  5. 2020Evolutionary learning of interpretable decision treescited by 15
  6. 2017Memory Augmented Control Networkscited by 13
  7. 2023Efficient Symbolic Policy Learning with Differentiable Symbolic Expressioncited by 10
  8. 2018Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programmingcited by 5
  9. 2021Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learningcited by 5
  10. 2023Discovering Adaptable Symbolic Algorithms from Scratchcited by 4
  11. 2021Trustworthy AI for Process Automation on a Chylla-Haase Polymerization Reactorcited by 1

Built on by

Not cited yet.