> Data, Materials, and Code Availability<p>> [...] However, sharing the AlphaZero algorithm code, network weights, or generated representation data would be technically infeasible at present.<p>Very interesting paper overall. However, the excuse that code sharing is "technically infeasible" is wearing thin nearly 5 years after the initial AlphaZero paper was released.
> Summary of Results<p>> Many Human Concepts Can Be Found in the AlphaZero Network.<p>> We demonstrate that the AlphaZero network’s learned representation of the chess board can be used to reconstruct, at least in part, many human chess concepts. We adopt the approach of using concept activation vectors (6) by training sparse linear probes for a wide range of concepts, ranging from components of the evaluation function of Stockfish (9), a state-of-the-art chess engine, to concepts that describe specific board patterns.<p>> A Detailed Picture of Knowledge Acquisition during Training.<p>> We use a simple concept probing methodology to measure the emergence of relevant information over the course of training and at every layer in the network. This allows us to produce what we refer to as what–when–where plots, which detail what concept is learned, when in training time it is learned, and where in the network it is computed. What–when–where plots are plots of concept regression accuracy across training time and network depth. We provide a detailed analysis for the special case of concepts related to material evaluation, which are central to chess play.<p>> Comparison with Historical Human Play.<p>> We compare the evolution of AlphaZero play and human play by comparing AlphaZero training with human history and across multiple training runs, respectively. Our analysis shows that despite some similarities, AlphaZero does not precisely recapitulate human history. Not only does the machine initially try different openings from humans, it plays a greater diversity of moves as well. We also present a qualitative assessment of differences in play style over the course of training.
I think this is great work. Interpretability is the worst problem in deep learning, as the lack of insight into what the model has learned prevents it from being useful for serious decision making.
I skimmed the article so sorry in advance if I missed it, but to me one fairly trivial way to gauge whether AlphaZero has human-like conceptual understanding of chess would be to throw a few games of Fischer random at it.<p>I remember with Deepminds breakout AI one very easy way to see the difference to human play was to change the shape of the paddle. Even very slight changes completely threw the AI off, so it was obvious it hadn't understood the 'breakout ontology' in a human way.<p>I'd expect the same from chess. Humans who understand chess at a high level well obviously play worse in non-standard variants but the familiar concepts are still in play. If an AI has a human-like grasp of high level concepts it ought to be pretty robust to some changes to the game rules like changing the dimensionality of the board.
I think many chess players will agree that latest chess engines (Stockfish NNUE/Leela) are playing better conceptually, so it's less useful to use older ones (SF8/A0) to study learned concepts. Still cool work tho.
Anyone know how this differs from a similar-seeming paper that was published a year ago?<p><a href="https://en.chessbase.com/post/acquisition-of-chess-knowledge-in-alphazero" rel="nofollow">https://en.chessbase.com/post/acquisition-of-chess-knowledge...</a>
<a href="https://arxiv.org/pdf/2111.09259.pdf" rel="nofollow">https://arxiv.org/pdf/2111.09259.pdf</a>
Here is a thought experiment for beating AlphaZero. Randomly select 10K children at a very young age (say 3), have them play chess against AlphaZero but simply have them move the exact move suggested by AlphaZero (i.e. basically this is AlphaZero playing itself). Play 10 games per day for 10 years.<p>The hypothesis is some children will deeply embed the algorithms into their own playing style - leveraging the subconscious to the greatest degree possible. Basically, we are training the human mind in the same way that we train AI. Would it work? Probably not, but our current approach (studying openings, etc.) is obviously not working so it makes sense to try something new.
I always wondered if a chess engine would learn better/faster if the opening positions and piece movement rules were randomized. Has anyone tried this?