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.
@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}
}