Cross Validated
Profile Activity
Meta user
Network profile
143
reputation
5

Hunnam

Apparently, this user prefers to keep an air of mystery about them.

1
answer
11
questions
~525
people reached
  • Member for 1 year
  • 9 profile views
  • Last seen Jul 6 at 20:25

Communities (11)

Top network posts

We respect a laser-like focus on one topic.

Top tags (15)

Score 0
Posts 10
Posts % 83
Score 0
Posts 9
Score 0
Posts 7
Score 0
Posts 6
Score 0
Posts 4
Score 0
Posts 4
View all tags →

Top posts (12)

All Questions Answers
Votes Newest
2 Using IPS(inverse probability weighting) with a deterministic policy as the logging policy Aug 12 '19
1 off-policy evaluation in reinforcement learning Jan 21
0 Weighted importance sampling (WIS) and Importance sampling (IS) Apr 30
0 Why does weighted importance sampling work? Apr 30
0 Batch computation vs online computation Aug 15 '19
0 way to transform reinforcement learning problems to bandit problems Sep 1 '19
0 Why is having low variance important in offline policy evaluation of reinforcement learning? Sep 29 '19
0 large variance from inverse probability weighting (inverse propensity score) Jun 25 '19
0 quick questions about a contextual bandit problem Jul 29 '19
0 Policy evaluation in contextual bandit setting Aug 4 '19
View all questions and answers →

Badges (5)

Gold

—

Silver

—

Bronze

5

Rarest