（待续）【转载】 DeepMind发Nature子刊：通过元强化学习重新理解多巴胺

原文地址：

http://www.dataguru.cn/article-13548-1.html

-------------------------------------------------------------------------------

https://baijiahao.baidu.com/s?id=1625146459890383305&wfr=spider&for=pc

https://link.springer.com/content/pdf/10.1023%2FA%3A1007379606734.pdf

https://link.springer.com/article/10.1023/A:1007379606734

https://www.baidu.com/s?tn=80035161_2_dg&wd=Multitasklearning

https://blog.csdn.net/wuguangbin1230/article/details/78223996

http://www.pianshen.com/article/2477158462/

https://arxiv.org/abs/1706.05098

https://blog.csdn.net/chanbo8205/article/details/83958564

https://github.com/intel-isl/MultiObjectiveOptimization

http://baijiahao.baidu.com/s?id=1600509777750939986&wfr=spider&for=pc

https://www.jiqizhixin.com/articles/2018-05-15-11

https://www.colabug.com/2695961.html

https://www.cnblogs.com/wangxiaocvpr/p/9448200.html

https://www.researchgate.net/publication/328332161_ProMP_Proximal_Meta-Policy_Search

http://papers.nips.cc/paper/7776-meta-reinforcement-learning-of-structured-exploration-strategies

https://www.ctolib.com/mip/Meta-RL.html

https://www.colabug.com/3907065.html

相关的主题：

• ICML 2018 | 从强化学习到生成模型：40篇值得一读的论文
• Minigo: AlphaGo Zero算法的开源实现
• 视觉推理（Visual Reasoning），神经网络也可以有逻辑
• DeepMind提出新型架构IMPALA：帮助实现单智能体的多任务强化学习
• python实现的DES加密算法和3DES加密算法实例
• 多级反馈队列调度算法（附Python3实现代码）
• 机器学习决策树算法实战：理论 + 详细的 Python 3 代码实现
• 基于TensorFlow打造强化学习API：TensorForce是怎样炼成的？