Nukplex: An Efficient Local Search Algorithm for Maximum K-Plex Problem

Abstract

Deep reinforcement learning (DRL) has achieved remarkable success in dynamic decision-making tasks. However, its inherent opacity and cold start problem hinder transparency and training efficiency. To address these challenges, we propose HRL-ID, a neural-symbolic framework that combines automated rule discovery with logical reasoning within a hierarchical DRL structure. HRL-ID dynamically extracts first-order logic rules from environmental interactions, iteratively refines them through success-based updates, and leverages these rules to guide action execution during training. Extensive experiments on Atari benchmarks demonstrate that HRL-ID outperforms state-of-the-art methods in training efficiency and interpretability, achieving higher reward rates and successful knowledge transfer between domains.

Cite

Text

Sun et al. "Nukplex: An Efficient Local Search Algorithm for Maximum K-Plex Problem." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/777

Markdown

[Sun et al. "Nukplex: An Efficient Local Search Algorithm for Maximum K-Plex Problem." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/sun2024ijcai-nukplex/) doi:10.24963/ijcai.2024/777

BibTeX

@inproceedings{sun2024ijcai-nukplex,
  title     = {{Nukplex: An Efficient Local Search Algorithm for Maximum K-Plex Problem}},
  author    = {Sun, Rui and Wang, Yiyuan and Wang, Shimao and Li, Hui and Li, Ximing and Yin, Minghao},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {7029-7037},
  doi       = {10.24963/ijcai.2024/777},
  url       = {https://mlanthology.org/ijcai/2024/sun2024ijcai-nukplex/}
}