Matthew Jackson @JacksonMattT · 18 Apr 2025
⁉️ While trying to find the best hyperparameter setting of ORL algorithms using a bandit, we noticed something unexpected: 🤯 After evaluating the episodic returns of more and more policies online, the bandit's performance *decreased*! https://t.co/LDvyBPyA2d https://t.co/1IKSA4DSaO
5 317Views
19Likes
5Reposts
1Replies
3Quotes
0Bookmarks
Is that a lot?
1.76×vs under 10K median3 020 views is typical
5.4× audienceReachviews ÷ followers
0.53%Engagement rateof viewers reacted