Search Results for author: János Kramár

Found 7 papers, 4 papers with code

Explaining grokking through circuit efficiency

no code implementations5 Sep 2023 Vikrant Varma, Rohin Shah, Zachary Kenton, János Kramár, Ramana Kumar

One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, transition to perfect generalisation.


Learning Reciprocity in Complex Sequential Social Dilemmas

no code implementations19 Mar 2019 Tom Eccles, Edward Hughes, János Kramár, Steven Wheelwright, Joel Z. Leibo

We analyse the resulting policies to show that the reciprocating agents are strongly influenced by their co-players' behavior.

Cannot find the paper you are looking for? You can Submit a new open access paper.