arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08115cs.LGcs.AI
收藏

加速强化学习的人类启发式框架

Human-Inspired Framework to Accelerate Reinforcement Learning

Stockholm University(斯德哥尔摩大学)

Ali Beikmohammadi, Sindri Magnússon

AI总结:

针对强化学习样本效率低的问题,提出一种人类启发式框架,通过先学习逐步变难的简单任务再迁移到主任务,无需预训练且不增加计算量,适配多种RL算法,经实验验证可有效提升样本效率。

摘要:

强化学习(RL)是数据科学决策的核心技术,但存在样本效率低下的问题,在物理交互成本高昂的真实场景中尤为突出。本文提出一种受人类学习启发的新型框架,用于提升RL算法的样本效率。其实现方式为:先让学习智能体接触难度逐步提升的简单任务,最终过渡到主任务。该方法无需预训练,仅需对简单任务进行一轮迭代学习,所得知识可支撑价值迁移、策略迁移等多种迁移学习方法,且不会增加计算复杂度。它适用于不同目标、环境及RL算法,包括基于价值、基于策略、表格型和深度RL方法。实验评估通过简单的Random Walk(随机游走)和更复杂的带约束最优控制问题,验证了该框架提升样本效率的有效性,在难度较高的主任务中表现尤为显著。

英文摘要:

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to enhance RL algorithm sample efficiency. It achieves this by initially exposing the learning agent to simpler tasks that progressively increase in complexity, ultimately leading to the main task. This method requires no pre-training and involves learning simpler tasks for just one iteration. The resulting knowledge can facilitate various transfer learning approaches, such as value and policy transfer, without increasing computational complexity. It can be applied across different goals, environments, and RL algorithms, including value-based, policy-based, tabular, and deep RL methods. Experimental evaluations demonstrate the framework's effectiveness in enhancing sample efficiency, especially in challenging main tasks, demonstrated through both a simple Random Walk and more complex optimal control problems with constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑