Grandmaster-Level Chess Without Search

Re:Grandmaster-Level Chess Without Search by ogogmad on Thursday February 08, 2024 @06:05PM (#39309035)

The point -- which I don't think you got -- is that extremely generic ingredients like high-quality data (which is the point of Stockfish here) and very deep Transformer-type Neural Networks, are enough to nearly match the performance of ad-hoc, non-generalisable techniques like gametree search algorithms.

This has two possible applications: 1. There's far less need to invent techniques like MCTS in the first place. 2. A single AI might be able to play grandmaster level chess by accident.

The catch is you need high quality data in large amounts.

[ Parent | on HN ]

Re:Grandmaster-Level Chess Without Search by YeGoblynQueenne on Thursday February 08, 2024 @06:08PM (#39309061)

I did get the point and I'm commenting that the point is missing the point. There is nothing new in learning that a large neural net can approximate the output of a classical system. This has been done many times before. The real point is that DeepMind build a system that is half-search and pretend it's no-search. You cannot get the "high-quality data" without a classical system- not in chess.

[ Parent | on HN ]

Re:Grandmaster-Level Chess Without Search by ogogmad on Thursday February 08, 2024 @06:19PM (#39309169)

I get your point. Acquiring the data is the hard part, and they cheated to get it. It's chicken and egg indeed.

[ Parent | on HN ]