Talk:Sample complexity

The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

This is the talk page for discussing improvements to the Sample complexity article.
This is not a forum for general discussion of the article's subject.

Put new text under old text. Click here to start a new topic.
New to Wikipedia? Welcome! Learn to edit; get help.

Article policies

Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL

Some keypoints for updating the article

Metric Learning Sample Complexity [3]
"low Sample Complexity" is more efficient [1]
Model based Reinforcement learning has a lower sample complexity [2]
sample complexity of Monte-Carlo Tree Search [4]

Literature

[1] Fidelman, Peggy, and Peter Stone. "The chin pinch: A case study in skill learning on a legged robot." Robot Soccer World Cup. Springer, Berlin, Heidelberg, 2006.
[2] Kurutach, Thanard, et al. "Model-ensemble trust-region policy optimization." arXiv preprint arXiv:1802.10592 (2018).
[3] Verma, Nakul, and Kristin Branson. "Sample complexity of learning mahalanobis distance metrics." Advances in neural information processing systems. 2015.
[4] Kaufmann, Emilie, and Wouter M. Koolen. "Monte-carlo tree search by best arm identification." Advances in Neural Information Processing Systems. 2017.

--ManuelRodriguez (talk) 16:19, 25 March 2020 (UTC)[reply]

Sample efficiency in Reinforcement learning

Not sure this is the same. It is discissed here as well: https://ai.stackexchange.com/questions/38775/do-the-terms-sample-complexity-and-sample-efficiency-mean-the-same-thing-in I would love to know more. Could somebody add information from a reputable source? Biggerj1 (talk) 19:13, 22 January 2024 (UTC)[reply]