alpha-zero-boosted
katrain
Our great sponsors
alpha-zero-boosted | katrain | |
---|---|---|
2 | 55 | |
79 | 1,490 | |
- | - | |
3.2 | 2.6 | |
almost 4 years ago | about 1 month ago | |
Python | Python | |
- | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
alpha-zero-boosted
-
DeepMind has open-sourced the heart of AlphaGo and AlphaZero
> I came up with a nifty implementation in Python that outperforms the naive impl by 30x, allowing a pure python MCTS/NN interop implementation. See https://www.moderndescartes.com/essays/deep_dive_mcts/
Great post!
Chasing pointers in the MCTS tree is definitely a slow approach. Although typically there are < 900 "considerations" per move for alphazero. I've found getting value/policy predictions from a neural network (or GBDT[1]) for the node expansions during those considerations is at least an order of magnitude slower than the MCTS tree-hopping logic.
[1] https://github.com/cgreer/alpha-zero-boosted
-
MuZero: Mastering Go, chess, shogi and Atari without rules
What you can do is checkout the algorithm at a particular stages of development. AlphaZero&Friends start out not being very good at the game, then over time they learn and become super human. You typically checkpoint the weights for the model at various stages. So early on, the algo would be like a 600 elo player for chess and then eventually get to superhuman elo levels. So if you wanted to train you can gradually play against versions of the algo until you can beat them by loading up the weights at various difficulty stages.
I implemented AlphaZero (but not Mu yet) using GBDTs instead of NNs here if you're curious about how it would work: https://github.com/cgreer/alpha-zero-boosted. Instead of saving the "weights" for a GBDT, you save the splitpoints for the value/policy models, but the concept is the same.
katrain
-
How do I record a played game on Fox?
I like Sabaki, but there's also GoWrite, CGoban (the KGS client), and others (search for "SGF editor"). You can also review .sgf with OGS online, or with AI Sensei. KaTrain is a very good AI client that can review .sgf as well.
-
Strongest AI program to play for free or little money?
The easiest way to install & use KataGo is via KaTrain: https://github.com/sanderland/katrain
-
Recording physical board games
I bring in my laptop with KaTrain installed and ask if my opponent is down for entering in the moves as we play as reviewing after. Its fun to check out different models, analysis depths, and local areas
-
Running KaTrain on Mac
I run KaTrain on my older Intel Mac with no issues. The OS is older, 12.6.3 (Monterey). I use the KaTrainOSX.dmg released by the KaTrain project. How did you install KaTrain?
-
Researchers found a strategy with which they can beat KataGo 97% of all time and other AI's. This strategy can successfully be used by amateur players who win against superhuman AI's in Go.
If you have a good computer you can run katago locally using something like katrain which makes installing it simpler and comes with options like controlling katago's strength.
-
Force katago/sabaki to always rate the move that was actually played?
If you are set on using Sabaki specifically I can't offer much advice since I don't have much experience with it, but what I can say is that I personally use Katrain to run Katago and I highly recommend it. If you want to try it out, you can just go here for the latest version as of today. Just scroll to the bottom and download "katrain.exe". It has many many very useful features - and of course will always evaluate the move that was actually played.
- What's your 5 tips to become a better player?
- New release of KaTrain includes updated katago with some interesting new features, including a new type of network!
-
turn off bad policy moves in katrain?
You can create an issue in https://github.com/sanderland/katrain/issues. The author actively resolves issues there.
-
Best LOCAL software for AI analysis
I use KaTrain. It's great. https://github.com/sanderland/katrain/releases
What are some alternatives?
KataGo - GTP engine and self-play learning in Go
lizzie - Lizzie - Leela Zero Interface
neural_network_chess - Free Book about Deep-Learning approaches for Chess (like AlphaZero, Leela Chess Zero and Stockfish NNUE)
adversarial-robustness-toolbox - Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
online-go.com - Source code for the Online-Go.com web interface
leela-zero - Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
Upsided-Sabaki-Themes - Various themes for the Sabaki go app
mars - Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
lizgoban - Leela Zero & KataGo visualizer
mctx - Monte Carlo tree search in JAX
lila - ♞ lichess.org: the forever free, adless and open source chess server ♞