Jürgen Schmidhuber @SchmidhuberAI · 02 Sep 2026
This "recurrent depth" is essentially what's in Sec. 5.3 of the 2015 paper: On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models https://t.co/0sqotWZqxp. This paper went beyond the
210 411Views
820Likes
49Reposts
23Replies
24Quotes
514Bookmarks
Is that a lot?
1.00×vs this author's median210 411 views is typical
43Percentile for this authorof 7 recent posts
9.61×vs 100K–1M median21 891 views is typical
97.31%Reachviews ÷ followers
0.43%Engagement rateof viewers reacted