Nine Chess Variants

Remember the post Non-random, Non-castling (December 2019)? It went something like this:-

Former World Champion Vladimir Kramnik has an idea: '[VK and DeepMind] tasked AlphaZero with exploring a variant that prevented either side from castling, trying different opening moves from both sides.'

If you don't remember that post, it's probably because you don't follow my chess960 blog, where it appeared. GM Kramnik resurfaced this month with a slew of similar ideas. You can explore them in New AlphaZero Paper Explores Chess Variants (chess.com):-

In a new paper from DeepMind, this time co-written by 14th world chess champion Vladimir Kramnik, the self-learning chess engine AlphaZero is used to explore the design of different variants of the game of chess, with different sets of rules.

While I was writing this current post, Chess.com updated their page to announce:-

On Friday, September 18 at noon Pacific time (21:00 Central Europe) Chess.com is hosting a round-table discussion streamed live on Chess.com/TV with GM Vladimir Kramnik, IM Danny Rensch and researchers of Deepmind discussing their latest paper in which AlphaZero explores chess variants.

Since that discussion will take place after my bedtime, I'll come back to it next week. It's been a while since I last ran a series on AI/NN, like these:-

• 2018-07-27: Chess Piece Recognition • 'Let's return to the series last seen in The Limits of Image Recognition (June 2018).'
• 2019-03-08: Closing an AI/NN Chapter • 'It's finally time to close the AI/NN series that I've been running for the last five months.'
• 2019-09-13: Beyond AlphaZero • 'For the last two months, I've used this blog's Friday post to wander around topics relevant to AlphaZero.'

GM Kramnik's latest ideas might promise a wealth of new material related to AI/NN.