Acquisition of Chess Knowledge in AlphaZero · HackerPapers discussions

Acquisition of Chess Knowledge in AlphaZero — mentioned by azakai

Mon, 09 Feb 2026 15:57:12 GMT

> AlphaGo or AlphaZero didn’t need to model human cognition. It needed to see the current state and calculate the optimal path better than any human could. I don't think this is right: To calculate the optimal path, you do need to model human cognition. At least, in the sense that finding the best path requires figuring out human concepts like "is the king vulnerable", "material value", "rook activity", etc. We have actual evidence of AlphaZero calculating those things in a way that is at least somewhat like humans do: https://arxiv.org/abs/2111.09259 So even chess has "hidden state" in a…

Paper and discussion history. A mention is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — mentioned by dsjoerg

Sun, 20 Nov 2022 19:34:31 GMT

Anyone know how this differs from a similar-seeming paper that was published a year ago? https://en.chessbase.com/post/acquisition-of-chess-knowledge... https://arxiv.org/pdf/2111.09259.pdf

Paper and discussion history. A mention is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — mentioned by Vetch

Fri, 03 Dec 2021 05:43:15 GMT

It looks like the basic meta-algorithm is: 1) Notice a pattern in the mathematics 2) Device a neural network that leverages structural properties of the space you wish to investigate 3) Encode relationship in a manner allowing use of supervised learning and see if the net can learn a pattern. 4) If it failed, rethink pattern and go back to step 2 or give up; else use attribution and explainability tools to try and extract human understandable concepts. Go back to step 2 until human converges 5) Use the extracted concepts to generate a conjecture or aid a proof. 6) Profit In a way it's like…

Paper and discussion history. A mention is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — HN submission

Mon, 22 Nov 2021 15:14:34 GMT

Acquisition of Chess Knowledge in AlphaZero

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — HN submission

Sat, 20 Nov 2021 19:58:18 GMT

Acquisition of Chess Knowledge in AlphaZero

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — HN submission

Fri, 19 Nov 2021 10:55:30 GMT

Acquisition of Chess Knowledge in AlphaZero (Deepmind 2021)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — mentioned by porphyra

Fri, 19 Nov 2021 00:45:10 GMT

Why link to Chessbase instead of to the arxiv paper directly? https://arxiv.org/abs/2111.09259 Chessbase is notoriously sketchy and there is a lawsuit against them for blatantly stealing GPL code. https://stockfishchess.org/blog/2021/our-lawsuit-against-che...

Paper and discussion history. A mention is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — mentioned by sarosh

Fri, 19 Nov 2021 00:21:54 GMT

The paper itself is here: https://arxiv.org/abs/2111.09259 with the key conclusion that "Examining the evolution of human concepts using probing showed that many human concepts can be accurately regressed from the AZ network after training, even though AlphaZero has never seen a human game of chess, and there is no objective function promoting human-like play or activations" and "[t]he fact that human concepts can be located even in a superhuman system trained by self-play broadens the range of systems in which we should expect to find human-understandable concepts"

Paper and discussion history. A mention is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — HN submission

Thu, 18 Nov 2021 23:58:53 GMT

Acquisition of Chess Knowledge in AlphaZero [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Acquisition of Chess Knowledge in AlphaZero — HN submission

Thu, 18 Nov 2021 02:08:46 GMT

Acquisition of Chess Knowledge in AlphaZero

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.