arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.03291cs.LGcs.AI
收藏

比较NARS与强化学习:ONA与$Q$-Learning算法的分析

Comparing NARS and Reinforcement Learning: An Analysis of ONA and $Q$-Learning Algorithms

Stockholm University(斯德哥尔摩大学)

Ali Beikmohammadi, Sindri Magnússon

AI总结:

本文比较了非公理推理系统NARS的实现ONA与$Q$-Learning在Open AI gym环境中的性能,发现NARS是强化学习的潜在替代方案,尤其在非确定性环境中表现优异。

摘要:

近年来,强化学习(RL)已成为解决机器学习中序列任务的主流方法。然而,寻找RL的合适替代方案仍是一个令人兴奋且创新的研究领域。其中一个备受关注的替代方案是非公理推理系统(NARS),这是一种通用认知推理框架。在本文中,我们深入探讨了NARS作为RL替代方案在解决序列任务方面的潜力。为了研究这一点,我们比较了ONA(作为NARS的实现)与$Q$-Learning在Open AI gym创建的各种环境中的性能。这些环境具有从简单到复杂的难度级别。结果表明,NARS是RL的潜在替代方案,在多样化环境中表现出有竞争力的性能,尤其是在非确定性环境中。

英文摘要:

In recent years, reinforcement learning (RL) has emerged as a popular approach for solving sequence-based tasks in machine learning. However, finding suitable alternatives to RL remains an exciting and innovative research area. One such alternative that has garnered attention is the Non-Axiomatic Reasoning System (NARS), which is a general-purpose cognitive reasoning framework. In this paper, we delve into the potential of NARS as a substitute for RL in solving sequence-based tasks. To investigate this, we conduct a comparative analysis of the performance of ONA as an implementation of NARS and $Q$-Learning in various environments that were created using the Open AI gym. The environments have different difficulty levels, ranging from simple to complex. Our results demonstrate that NARS is a promising alternative to RL, with competitive performance in diverse environments, particularly in non-deterministic ones.

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。

↑