人类基于错误的学习与现代深度RL算法的关系
Michele Garibbo1, Casimir J H Ludwig2, Nathan F Lepora3
1Department of Engineering Mathematics, Faculty of Engineering, University of Bristol, Bristol BS8 1QU, U.K. michele.garibbo@bristol.ac.uk.
这项研究揭示了深度强化学习 (RL) 与基于人类错误的学习有所不同. 一个新的算法,基于模型的确定性政策梯度 (MB-DPG),弥合了这一差距,提高了学习速度和稳定性.
科学领域:
- 认知科学 认知科学
- 机器学习 机器学习
- 神经科学是一个神经科学.
背景情况:
- 基于人类错误的学习利用定向错误进行行动更新.
- 深度强化学习 (RL) 采用类似更新的标量级奖励.
- 劳动力和人类学习之间的关系仍然未被充分探索.
研究的目的:
- 系统地比较主要的深度RL算法与基于人类错误的学习.
- 开发一种由人类学习机制启发的新型RL算法.
- 评估新算法的性能和稳定性.
主要方法:
- 对三大深度RL算法家族的比较分析与基于人类错误的学习.
- 使用镜子反转扰动实验来评估差异.
- 开发和测试一种新的基于模型的确定性政策梯度 (MB-DPG) 算法.
主要成果:
- 所有三个主要的深度RL方法都显示了与基于人类错误的学习的定性差异.
- 在镜子反转和旋转扰动下,MB-DPG成功捕获了基于人类错误的学习.
- 与标准的RL算法相比,MB-DPG在复杂的任务上表现出更快的学习速度和更强大的模型错误规格稳定性.
结论:
- 深度RL算法从根本上不同于基于人类错误的学习.
- MB-DPG提供了一种有希望的方法来弥合这一差距,增强RL的能力.
- 这些发现表明了开发更类似人类的人工智能学习系统的新方向.
更多相关视频
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
相关概念视频
Associative Learning
Classical conditioning, also known...
Law of Effect
Edward Thorndike's foundational work involved studying learning in animals, particularly using puzzle...
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Purposive Learning
Reinforcement
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
Generalization, Discrimination, and Extinction
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
