gRR comments on Problematic Problems for TDT - LessWrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (298)
The problems look like a kind of an anti-Prisoner's Dilemma. An agent plays against an opponent, and gets a reward iff they played differently. Then any agent playing against itself is screwed.