AlphaZero/Kramnik: More variants

Modifying the existing rules for chess to make it more dynamic or decisive, is a non-trivial task: you need years of experience and large numbers of people playing new versions in order to assess the quality and appeal of any new variant. Former World Champion Vladimir Kramnik has proposed new variants, and DeepMind has used their AI technology to evaluate them in a much shorter period of time. Here are their findings for No-castling, Pawn one square and Stalemate=win chess.

THE INTERESTING WORLD OF CHESS VARIANTS (PART II) – InquiScitive

GM Vladimir Kramnik on AlphaZero and achieving excellence

AI Ruined Chess. Now, It's Making the Game Beautiful Again

New AlphaZero Paper Explores Chess Variants

How AlphaZero Learns Chess?. DeepMind and Google Brain researchers

AlphaZero/Kramnik: Torpedo pawns

How AlphaZero Learns Chess?. DeepMind and Google Brain researchers

ACM: Digital Library: Communications of the ACM

DeepMind's AI is helping to re-write the rules of chess

How AlphaZero Learns Chess

THE INTERESTING WORLD OF CHESS VARIANTS (PART II) – InquiScitive

PDF) Acquisition of chess knowledge in AlphaZero

New AlphaZero Paper Explores Chess Variants

List of rule alterations proposed by Vladimir Kramnik and the

Kramnik and AlphaZero Blundering, Grossly