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.

ACM: Digital Library: Communications of the ACM

AlphaZero to analyse “no-castling” match of the champions

Acquisition of chess knowledge in AlphaZero

AlphaZero/Kramnik: Exploring new chess variants

AlphaZero really is that good

AlphaZero opening novelty hits the Tiger Modern with both rook

Reimagining Chess with AlphaZero, February 2022

How AlphaZero Learns Chess?. DeepMind and Google Brain researchers

The AlphaZero Papers: What You Need To Know!?

Assessing Game Balance with AlphaZero: Exploring Alternative Rule

ACM: Digital Library: Communications of the ACM

AlphaZero really is that good

Vladimir Kramnik proposes an exciting chess variant!