English

SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning

Machine Learning 2023-12-07 v1 Artificial Intelligence

Abstract

In this paper, we introduce a novel algorithm - the Skill-Driven Skill Recombination Algorithm (SDSRA) - an innovative framework that significantly enhances the efficiency of achieving maximum entropy in reinforcement learning tasks. We find that SDSRA achieves faster convergence compared to the traditional Soft Actor-Critic (SAC) algorithm and produces improved policies. By integrating skill-based strategies within the robust Actor-Critic framework, SDSRA demonstrates remarkable adaptability and performance across a wide array of complex and diverse benchmarks.

Keywords

Cite

@article{arxiv.2312.03216,
  title  = {SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning},
  author = {Eric H. Jiang and Andrew Lizarraga},
  journal= {arXiv preprint arXiv:2312.03216},
  year   = {2023}
}
R2 v1 2026-06-28T13:42:23.685Z