[cbutner]

This took about a year and a half – a little over a year coding in between experiments and training.

It's a chess engine with a primary neural network just like AlphaZero or Leela Chess Zero's, but it adds on a secondary "commentary decoder" network based on Transformer architecture to comment on positions and moves. All of the code and data for training and search is from scratch, although it does use Stockfish code to generate legal moves and manage chess positions.

You can watch it play on Lichess here: https://lichess.org/@/PlayChessCoach/tv or challenge it here: https://lichess.org/?user=PlayChessCoach#friend, and see its commentary in spectator chat. It only plays one game at a time, so you may need to wait a little bit. It's fairly strong (~3450 rating, roughly on par with Stockfish 12 or SlowChess Blitz 2.7), but you can set up a position when challenging it so that it's missing a couple pawns or a piece (Variant: From Position).

I ended up writing much more about it than I expected. If you're into the technical side of chess or machine learning, beyond the linked overview, there's:

High-level explanation: https://chrisbutner.github.io/ChessCoach/high-level-explanat...

Technical explanation: https://chrisbutner.github.io/ChessCoach/technical-explanati... (including code pointers)

Development process: https://chrisbutner.github.io/ChessCoach/development-process... (including timelines, bugs and failures)

Data: https://chrisbutner.github.io/ChessCoach/data.html (including raw measurements and tournament PGN files)

And the code is here: https://github.com/chrisbutner/ChessCoach (C++ and Python, GPLv3 or later)

Happy to answer any questions!

[mcyc]

This is a fantastic project. Thanks for sharing!

I had a nice long conversation with two of the authors of [0] at ACL.

One thing we discussed was the reverse problem. That is, as a player, could I give commands to the model and have the engine figure the moves that would best satisfy them.

This ranges from concrete like "take the black square bishop" (there is still variability like which piece should take it or if it's even possible) to more complex positional stuff like "set up to attack the kingside."

Any thoughts on this line of research?

[0] Automated Chess Commentator Powered by Neural Chess Engine (Zang, Yu & Wan, 2019) https://arxiv.org/pdf/1909.10413.pdf

[cbutner]

SentiMATE[1] looks at one of the reverse problems in a way - training an engine on commentary data - although it's not exactly what you're talking about.

I think this line of thinking could eventually lead to automated metrics for commentary evaluation, which could in turn lead to better methods than top-k/top-p for turning a bunch of sequential logits into a sentence or paragraph - basically treat it like MCTS/PUCT also.

The problem is that if you look at high-level commentary - maybe Radjabov-MVL on https://www.chess.com/news/view/2021-champions-chess-tour-fi... (I'm not the best judge, just a quick search) - it's not often possible to predict the move starting with the comment. And if you did, you might end up with very dry metrics and reverse commentary.

But this direction has a lot of potential I think, beyond just chess, into more of an algorithmic/generational support for pure NN-based language models.

[1] https://arxiv.org/pdf/1907.08321.pdf

[modeless]

Where did you source the commentary dataset?

[dmurray]

Not the author, but ChessBase sell a product (Megabase) which includes 85,000 annotated games in a more-or-less machine readable format. [0]

To me it's probably OK to train a model on this, at least for hobby purposes, though some GitHub Copilot critics might disagree. And a large part of ChessBase's business model is based on ripping off other people's IP and presenting it as their own [1]. But still, I can see why the author might want to be coy about answering this question.

[0] https://en.chessbase.com/post/new-mega-database-2021

[1] https://lichess.org/blog/YCvy7xMAACIA8007/fat-fritz-2-is-a-r...

[shmageggy]

Seconded. I looked around the writeup site for a bit and couldn't figure that out. That's arguably the most important piece of info about this project.

[gowld]

Can you have it play more games by giving it less time per turn (~2500 rating is plenty good for an opponent/coach) and playing games concurrently while it waits for human to play?

how much does a game cost in CPU time money?

How do I get the commentary for a game I played? Oh, it's in Analysis page.

It plays chess very well, but the commentary is incoherent and doesn't match the game well -- The attacks described are nonsense and the coordinates are wrong. It seems a little confused about which side is which? It thinks a rook can diagonally attack a bishop, and seems to name squares opposite from their actual name.

[cbutner]

That's a good idea. A bigger problem than time-slicing is probably GPU/TPU device ownership issues and GPU/TPU memory usage with multiple games going in parallel. There may be some ways to multiplex it intelligently though.

Costs are difficult to work out - it depends on cloud vs. self-hosting, what kind of TPUs/GPUs, how long you're calculating over.

The advantage that classical/NNUE engines have is that they can more easily spread over distributed frameworks like Fishtest.

[dmurray]

> the commentary is incoherent and doesn't match the game well > The attacks described are nonsense and the coordinates are wrong.

Agreed, this looks superficially like commentary on the game, but honestly it doesn't seem more pertinent to the game score than a Markov chain trained on all the commentary would be (presumably this isn't true, and the author started with something like that Markov chain and the current version is way better in terms of some fitness function).

I wonder if there just is not enough training data available. GPT-3 overcomes this by harvesting a ridiculous amount of training data. AlphaZero, and the chess engine here, which is excellent, overcome it by generating their own training data through self play. But that's not applicable to the task of generating commentary.

[evanhu_]

I'm super impressed with what you've managed to create, do you have any further plans with this project? I'm curious now that it's finished and documented to such an extent will you try to bring it publicity and actual usage or was this just a passion project. Thanks

[cbutner]

Thank you! I do get that itch to jump in and improve things whenever I see it lose a game, but I don't have further plans (development or commercial) in the near-term. The goal originally was to see whether I liked ML, to decide on my next industry/career move, but there was a lot of "one more month".

I'm actually hopeful that some search techniques such as SBLE-PUCT[1] or better derivations can make their way into other open source projects, but they've had big teams working for a while on similar, often better ideas, so we'll have to see.

[1] https://chrisbutner.github.io/ChessCoach/high-level-explanat...

[mxwsn]

So, do you like ML?

[cbutner]

Haha - I dislike how much of a black box it is, despite the statistical basis (for example, the back and forth on batch normalization rationale). But lots of interesting problems and tech to dig into.

[ritchiea]

You estimate it’s rated 3400-ish and it loses games????

[cbutner]

It loses some games to Stockfish 13 and 14, and Lc0 - rarely at slow time control, and more often at blitz and bullet (actually, it has losses all the way down to Stockfish 9 in blitz).

Partly because of the way it tries to search more widely to avoid tactical traps, it can also be a little sloppy in holding advantages or minimizing losses (this could use some more work and tuning). This ends up making it a little drawish, so it loses less than you'd expect to Stockfish 14, but also doesn't beat up weaker engines as well as Stockfish 14 does.

You can see some of this in the raw tournament results[1]. At 40 moves per 15 minutes, repeating, each engine draws with the ones above and below it, but starts to win and lose at a distance of 2 or 3.

At 5+3 time control, ChessCoach goes 1-0-29 vs. Stockfish 12, but Stockfish 12 is better at beating Stockfish 8-11 than ChessCoach is, so CC ends up between SF11 and SF12 in the end.

On Lichess, where there's no "free time" to get ready for searches, ChessCoach's naïve node allocation/deallocation makes it waste time, and means it can't ponder for very long on the opponent's time - a big opportunity for improvement (it needs a multi-threaded pool deallocator that can feed nodes back to local pools for the long-lived search threads). I think it's also hitting a bug with Syzygy memory mapping that Stockfish works around via reloading every "ucinewgame" (which I don't trigger on Lichess). So, overall, its performance on Lichess is worse.

Also, you can't read too much into this data - very few games, and no opening book.

[1] https://chrisbutner.github.io/ChessCoach/data.html#appendix-...

[iooi]

> It only plays one game at a time, so you may need to wait a little bit

Why this limitation? Is it fairly computationally expensive to run?

[cbutner]

Yes, each bot uses a v3-8 Cloud TPU VM, and tries to be constantly playing a game. The search tree is also very memory-hungry. And right now it's also using the Python API for TensorFlow, which is likely wasting a lot of potential.

Lots of room for improvement!

[lemonade5117]

Could using something like AlphaZero.jl make it more efficient?

https://github.com/jonathan-laurent/AlphaZero.jl

[cbutner]

The engine itself is in C++, but it calls in to TensorFlow via Python as a portability/distribution vs. performance trade-off.

Next steps could be using one of Lc0's backends for GPU scenarios, or taking the other side of the trade and using the C++ API for TPU.

There's also your typical CPU and memory optimizations that could be made - some baseline work there but not targeted.

[lemonade5117]

I see. I guess compute intensive stuff is usually implemented in c++. By the way, if you don't mind, could you share your experience in learning RL? I am struggling through Sutton and Barto's text right now and wondering if I'll progress faster if I just "dive into things." Also, nice project!

[cbutner]

I think it always helps to have a project to apply things to as you're learning something, even if it means coming up with something small. While preparing, I found it helpful to read for at least an hour each morning, and then divided the rest of the day into learning vs. "diving in" as I felt like it.

Getting deep into RL specifically wasn't so necessary for me because I was just replicating AlphaZero there, although reading papers on other neural architectures, training methods, etc. helped with other experimentation.

You may be well past this, but my biggest general recommendation is the book, "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" to quickly cover a broad range of statistics, APIs, etc., at the right level of practicality before going further into different areas (for PyTorch, I'm not sure what’s best).

Similarly, I was familiar with the calculus underpinnings but did appreciate Andrew Ng's courses for digging into backpropagation etc., especially when covering batching.

[squirrelmaker]

I found "Foundations of Deep Reinforcement Learning - Theory and Practice in Python" by Laura Graesser and Wah Loon Keng quite helpful in that it was somewhat like get a excellent summary course in about 6 years of RL advancements. I will say that it's quite forthcoming with the math. Anyway, I just wanted to know how they (not sure exactly who did it first, I just meant people with machines) got RL to play Atarti Pitfall. So take any recommendation I make with a grain of salt.

[jmcguckin]

I’d like to self host. Will this run with a gpu?

[cbutner]

Yes! I haven't done as much testing with GPU, but did validate running with 4x V100s. You just need to adjust the "search_threads" option to the number of GPUs, but set it to at least 2.

Installation for GPU is covered here: https://github.com/chrisbutner/ChessCoach#installation (a little messy, sorry)