arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.10015cs.SIcs.AIcs.MAcs.NE
收藏

社会学习策略的元控制

Meta-control of social learning strategies

Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Eindhoven University of Technology(埃因霍温理工大学);DeepMind(深度思维);Korea Advanced Institute of Science and Technology(韩国科学技术院)

Anil Yaman, Nicolas Bredeche, Onur Çaylak, Joel Z. Leibo, Sang Wan Lee

摘要:

社会学习,即在没有实际经验的情况下模仿他人的行为,提供了一种成本效益高的知识获取方式。然而,它提出了一个基本问题,即哪些人拥有可靠的信息:成功的个人还是大多数人。前者和后者分别被称为基于成功的社会学习策略和顺从的社会学习策略。我们在这里表明,虽然成功为基础的战略充分利用低不确定性的良性环境,它失败的不确定性环境。另一方面,从众策略可以有效地缓解这种不利影响。基于这些发现,我们假设,元控制的个人和社会学习策略提供了有效的和样本效率的学习在动荡和不确定的环境。在一组具有不同波动性和不确定性的环境中进行的模拟证实了我们的假设。结果表明,社会学习的元控制提供代理的杠杆,以解决环境的不确定性,以最小的探索成本,通过利用他人的学习作为外部知识库。

英文摘要:

Social learning, copying other's behavior without actual experience, offers a cost-effective means of knowledge acquisition. However, it raises the fundamental question of which individuals have reliable information: successful individuals versus the majority. The former and the latter are known respectively as success-based and conformist social learning strategies. We show here that while the success-based strategy fully exploits the benign environment of low uncertainly, it fails in uncertain environments. On the other hand, the conformist strategy can effectively mitigate this adverse effect. Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments. Simulations on a set of environments with various levels of volatility and uncertainty confirmed our hypothesis. The results imply that meta-control of social learning affords agents the leverage to resolve environmental uncertainty with minimal exploration cost, by exploiting others' learning as an external knowledge base.

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。

↑