简体繁体 English

强化学习文献中的“软”是什么意思？

[英]What does "soft" in reinforcement learning literature mean?

原文 2019-11-27 13:11:33 1 2 machine-learning/ deep-learning/ artificial-intelligence/ reinforcement-learning

I have noticed that some papers refers to soft agents, and I thought that it was just an agent where the entropy is included in the objective function of the policy network.我注意到一些论文提到了软代理，我认为它只是一个熵包含在策略网络目标函数中的代理。 But now I'm not sure anymore.. Can anyone confirm or offer another explanation?但是现在我不确定了.. 任何人都可以确认或提供其他解释吗？

2 个解决方案

So, it seems like this is the case.所以，好像是这样的。 Asked about where the entropy enters SAC on ai.stackexchange and got a good answer for those interested.在ai.stackexchange上被问及熵从哪里进入 SAC，感兴趣的人得到了很好的答案。

An epsilon-soft policy is a policy that takes every action with a probability of at least epsilon in every state. epsilon-soft 策略是一种在每个状态下以至少 epsilon 的概率采取每个动作的策略。 (Source http://incompleteideas.net/sutton/book/RLbook2018.pdf exercise 4.6 page 82 (104 of the pdf)). （来源http://incompleteideas.net/sutton/book/RLbook2018.pdf练习 4.6 第 82 页（pdf 的 104））。 A soft policy is a policy that takes every action with positive probability (page 100/122).软策略是一种以正概率采取每个动作的策略（第 100/122 页）。

什么是强化机器学习？ - What is Reinforcement machine learning?

“朴素”贝叶斯在机器学习中意味着什么？ - What does “Naive” Bayes mean in Machine learning?

机器学习中的迭代意味着什么？ - What does iteration in Machine Learning mean?

clf在机器学习中是什么意思？ - What does clf mean in machine learning?

机器学习中的召回是什么意思？ - What does recall mean in Machine Learning?

机器学习中的“训练损失”是什么意思？ - What does the 'training loss' mean in machine learning?

NEAT和强化学习之间有什么关系？ - What is the relation between NEAT and reinforcement learning?

强化学习和深度RL有什么区别？ - What is the difference between reinforcement learning and deep RL?

强化学习中参数化策略的含义是什么？ - What is the meaning of paramaterized policy in Reinforcement learning?

强化学习 - Reinforcement Learning

暂无

暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 什么是强化机器学习？ - What is Reinforcement machine learning? “朴素”贝叶斯在机器学习中意味着什么？ - What does “Naive” Bayes mean in Machine learning? 机器学习中的迭代意味着什么？ - What does iteration in Machine Learning mean? clf在机器学习中是什么意思？ - What does clf mean in machine learning? 机器学习中的召回是什么意思？ - What does recall mean in Machine Learning? 机器学习中的“训练损失”是什么意思？ - What does the 'training loss' mean in machine learning? NEAT和强化学习之间有什么关系？ - What is the relation between NEAT and reinforcement learning? 强化学习和深度RL有什么区别？ - What is the difference between reinforcement learning and deep RL? 强化学习中参数化策略的含义是什么？ - What is the meaning of paramaterized policy in Reinforcement learning? 强化学习 - Reinforcement Learning

相关标签

粤ICP备18138465号 © 2020-2024 STACKOOM.COM