• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

通过强化学习进行的人工开发可以从多种动机中受益。

Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.

作者信息

Palm Günther, Schwenker Friedhelm

机构信息

Institute of Neural Information Processing, Ulm University, Ulm, Germany.

出版信息

Front Robot AI. 2019 Feb 14;6:6. doi: 10.3389/frobt.2019.00006. eCollection 2019.

DOI:10.3389/frobt.2019.00006
PMID:33501023
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7805942/
Abstract

Research on artificial development, reinforcement learning, and intrinsic motivations like curiosity could profit from the recently developed framework of multi-objective reinforcement learning. The combination of these ideas may lead to more realistic artificial models for life-long learning and goal directed behavior in animals and humans.

摘要

关于人工发育、强化学习以及诸如好奇心等内在动机的研究，可以从最近发展起来的多目标强化学习框架中获益。这些理念的结合可能会为动物和人类的终身学习及目标导向行为带来更现实的人工模型。

相似文献

1
Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.通过强化学习进行的人工开发可以从多种动机中受益。
Front Robot AI. 2019 Feb 14;6:6. doi: 10.3389/frobt.2019.00006. eCollection 2019.
2
Optimal Policy of Multiplayer Poker via Actor-Critic Reinforcement Learning.通过演员-评论家强化学习实现多人扑克的最优策略
Entropy (Basel). 2022 May 30;24(6):774. doi: 10.3390/e24060774.
3
Meta attention for Off-Policy Actor-Critic.用于离策略演员-评论家的元注意力机制
Neural Netw. 2023 Jun;163:86-96. doi: 10.1016/j.neunet.2023.03.024. Epub 2023 Mar 28.
4
Intrinsic motivation, curiosity, and learning: Theory and applications in educational technologies.内在动机、好奇心与学习：教育技术中的理论与应用
Prog Brain Res. 2016;229:257-284. doi: 10.1016/bs.pbr.2016.05.005. Epub 2016 Jul 29.
5
Curiosity-driven recommendation strategy for adaptive learning via deep reinforcement learning.基于深度强化学习的好奇心驱动推荐策略，用于自适应学习。
Br J Math Stat Psychol. 2020 Nov;73(3):522-540. doi: 10.1111/bmsp.12199. Epub 2020 Feb 21.
6
A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems.基于博弈论的人工系统内在动机激励模型框架。
Front Psychol. 2013 Oct 30;4:791. doi: 10.3389/fpsyg.2013.00791. eCollection 2013.
7
Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning.通过演员-评论家强化学习对肌电假肢控制器进行在线人工训练。
IEEE Int Conf Rehabil Robot. 2011;2011:5975338. doi: 10.1109/ICORR.2011.5975338.
8
The role of intrinsic motivations in attention allocation and shifting.内在动机在注意力分配和转移中的作用。
Front Psychol. 2014 Apr 1;5:273. doi: 10.3389/fpsyg.2014.00273. eCollection 2014.
9
Deep Reinforcement Learning on Autonomous Driving Policy With Auxiliary Critic Network.基于辅助评论家网络的自动驾驶策略深度强化学习
IEEE Trans Neural Netw Learn Syst. 2023 Jul;34(7):3680-3690. doi: 10.1109/TNNLS.2021.3116063. Epub 2023 Jul 6.
10
Combining backpropagation with Equilibrium Propagation to improve an Actor-Critic reinforcement learning framework.将反向传播与平衡传播相结合以改进演员-评论家强化学习框架。
Front Comput Neurosci. 2022 Aug 23;16:980613. doi: 10.3389/fncom.2022.980613. eCollection 2022.

引用本文的文献

1
Foundations of human spatial problem solving.人类空间问题解决的基础。
Sci Rep. 2023 Jan 27;13(1):1485. doi: 10.1038/s41598-023-28834-3.
2
Neural Networks With Motivation.具有动机的神经网络。
Front Syst Neurosci. 2021 Jan 11;14:609316. doi: 10.3389/fnsys.2020.609316. eCollection 2020.
3
Structure-Preserving Imitation Learning With Delayed Reward: An Evaluation Within the RoboCup Soccer 2D Simulation Environment.具有延迟奖励的结构保持模仿学习：在机器人世界杯足球2D模拟环境中的评估
Front Robot AI. 2020 Sep 16;7:123. doi: 10.3389/frobt.2020.00123. eCollection 2020.

本文引用的文献

1
Social learning through prediction error in the brain.大脑中通过预测误差进行的社会学习。
NPJ Sci Learn. 2017 Jun 16;2:8. doi: 10.1038/s41539-017-0009-2. eCollection 2017.
2
Over the river, through the woods: cognitive maps in the hippocampus and orbitofrontal cortex.越过河流，穿过树林：海马体与眶额皮质中的认知地图
Nat Rev Neurosci. 2016 Aug;17(8):513-23. doi: 10.1038/nrn.2016.56. Epub 2016 Jun 3.
3
Mastering the game of Go with deep neural networks and tree search.用深度神经网络和树搜索掌握围棋游戏。
Nature. 2016 Jan 28;529(7587):484-9. doi: 10.1038/nature16961.
4
Human-level control through deep reinforcement learning.通过深度强化学习实现人类水平的控制。
Nature. 2015 Feb 26;518(7540):529-33. doi: 10.1038/nature14236.
5
Learning of embodied interaction dynamics with recurrent neural networks: some exploratory experiments.利用递归神经网络学习具身交互动力学：一些探索性实验。
J Neural Eng. 2014 Apr;11(2):026019. doi: 10.1088/1741-2560/11/2/026019. Epub 2014 Mar 24.
6
"Notice of Violation of IEEE Publication Principles" Multiobjective Reinforcement Learning: A Comprehensive Overview.《违反IEEE出版原则通知》 多目标强化学习：全面概述
IEEE Trans Cybern. 2013 Apr 29. doi: 10.1109/TSMCC.2013.2249512.
7
Positive affect versus reward: emotional and motivational influences on cognitive control.积极情绪与奖励：情绪和动机对认知控制的影响。
Front Psychol. 2011 Oct 19;2:279. doi: 10.3389/fpsyg.2011.00279. eCollection 2011.
8
States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning.状态与奖励：基于模型和无模型强化学习的分离神经预测误差信号。
Neuron. 2010 May 27;66(4):585-95. doi: 10.1016/j.neuron.2010.04.016.
9
Reinforcement learning, conditioning, and the brain: Successes and challenges.强化学习、条件作用与大脑：成就与挑战。
Cogn Affect Behav Neurosci. 2009 Dec;9(4):343-64. doi: 10.3758/CABN.9.4.343.
10
Finding intrinsic rewards by embodied evolution and constrained reinforcement learning.通过具身进化和受限强化学习寻找内在奖励。
Neural Netw. 2008 Dec;21(10):1447-55. doi: 10.1016/j.neunet.2008.09.013. Epub 2008 Oct 9.