The document discusses distances between data and similarity measures in data analysis. It introduces the concept of distance between data as a quantitative measure of how different two data points are, with smaller distances indicating greater similarity. Distances are useful for tasks like clustering data, detecting anomalies, data recognition, and measuring approximation errors. The most common distance measure, Euclidean distance, is explained for vectors of any dimension using the concept of norm from geometry. Caution is advised when calculating distances between data with differing scales.
This document summarizes a presentation on offline reinforcement learning. It discusses how offline RL can learn from fixed datasets without further interaction with the environment, which allows for fully off-policy learning. However, offline RL faces challenges from distribution shift between the behavior policy that generated the data and the learned target policy. The document reviews several offline policy evaluation, policy gradient, and deep deterministic policy gradient methods, and also discusses using uncertainty and constraints to address distribution shift in offline deep reinforcement learning.
The document discusses distances between data and similarity measures in data analysis. It introduces the concept of distance between data as a quantitative measure of how different two data points are, with smaller distances indicating greater similarity. Distances are useful for tasks like clustering data, detecting anomalies, data recognition, and measuring approximation errors. The most common distance measure, Euclidean distance, is explained for vectors of any dimension using the concept of norm from geometry. Caution is advised when calculating distances between data with differing scales.
This document summarizes a presentation on offline reinforcement learning. It discusses how offline RL can learn from fixed datasets without further interaction with the environment, which allows for fully off-policy learning. However, offline RL faces challenges from distribution shift between the behavior policy that generated the data and the learned target policy. The document reviews several offline policy evaluation, policy gradient, and deep deterministic policy gradient methods, and also discusses using uncertainty and constraints to address distribution shift in offline deep reinforcement learning.
43. 共同研究はやっぱり大事
2018:CHI
IEEE TVCG
IEEE VR
2017:IEEE ISMAR
IEEE VR
2016:IEEE ISMAR
2015:IEEE VR
IEEE ISMAR
2014:IEEE ISMAR
2 G.
1 G.
1 G.
1 G.
3 G.3 G.
3 G. 1 G.
1 G.
2 G.
2 G.
3 G.
3 G. 3 G.
ConferenceX G.
X G.
Xグループ数
Journal track
1 G.
(2018: AH)
(2017: AH)
(2016: AH)
(2015: AH) 1 G.
2 G.
1 G.
1 G.
2 G.
2G
3 G. 2 G.
54. 査読の闇: The NIPS experiment
投稿のうち10%(166件)を、2つの査読委
員会の両方で審査した。
→委員会1で「採択された論文」の57%が委員
会2でリジェクトされた。
“ 57% of the papers accepted by the first
committee were rejected by the second one
and vice versa. In other words, most papers at
NIPS would be rejected if one reran the
conference review process (with a 95%
confidence interval of 40-75%”
”Computer science conference acceptances
seem to be more random than we had
previously realized.”
http://blog.mrtz.org/2014/12/15/the-nips-experiment.html
http://hunch.net/?p=467864