Difference between revisions of "ShashChess"
GerdIsenberg (talk | contribs) |
GerdIsenberg (talk | contribs) |
||
| Line 30: | Line 30: | ||
was applied in ShashChess since version 12.0 <ref>[https://groups.google.com/g/fishcooking/c/GLag32ARtKo/m/3Zoaq3-rAwAJ ShashChess 12.0] by [[Andrea Manzo]], [[Computer Chess Forums|FishCooking]], June 28, 2020</ref>. | was applied in ShashChess since version 12.0 <ref>[https://groups.google.com/g/fishcooking/c/GLag32ARtKo/m/3Zoaq3-rAwAJ ShashChess 12.0] by [[Andrea Manzo]], [[Computer Chess Forums|FishCooking]], June 28, 2020</ref>. | ||
After the end of a decisive game in selfplay with appropriate [[Depth|search depth]], the [[Move List|list of moves]] (ml) and associated [[Score|scores]] is merged into the learn table from end to start, replacements preferring depth and score, | After the end of a decisive game in selfplay with appropriate [[Depth|search depth]], the [[Move List|list of moves]] (ml) and associated [[Score|scores]] is merged into the learn table from end to start, replacements preferring depth and score, | ||
| − | the score of timestep t adjusted as weighted average with the future reward of timestep t+1, using a [https://en.wikipedia.org/wiki/Q-learning#Learning_Rate learning rate] α of 0.5 and a [https://en.wikipedia.org/wiki/Q-learning#Discount_factor discount factor] γ of 0.99: | + | the score of timestep t adjusted as weighted average with the future reward of timestep t+1, using a [https://en.wikipedia.org/wiki/Q-learning#Learning_Rate learning rate] α of 0.5 and a [https://en.wikipedia.org/wiki/Q-learning#Discount_factor discount factor] γ of 0.99 <ref>[https://github.com/amchess/ShashChess/blob/master/src/All/search.cpp#L2625 ShashChess/search.cpp at master · amchess/ShashChess · GitHub]</ref>: |
<pre> | <pre> | ||
for (t = ml.size() - 2; t >= 0; t--) { | for (t = ml.size() - 2; t >= 0; t--) { | ||
Revision as of 09:03, 4 June 2021
Home * Engines * Stockfish * ShashChess
ShashChess,
a Stockfish derivative by Andrea Manzo with the aim to apply the proposals of Alexander Shashin as exposed in his book Best Play: A New Method for Discovering the Strongest Move [1] [2]
[3].
First released in July 2018 [4],
subsequent ShashChess versions feature skill levels and handicap modes, NNUE, Monte-Carlo Tree Search with one or multiple threads in conjunction with alpha-beta,
and various learning techniques utilizing a persistent hash table [5]
[6].
Personalities
Based on static evaluation score ranges derivered from pawn endgame point value (PawnValueEg = 208), ShashChess classifies the position with five personalities of three former World Chess Champions, Tigran Petrosian for negative scores, José Raúl Capablanca for balanced scores, and Mikhail Tal for positive scores [7]:
if (eval < -74) personality = Petosian; else if (eval < -31) personality = Petosian | Capablanca; else if (eval < 31) personality = Capablanca; else if (eval < 74) personality = Capablanca | Tal; else personality = Tal;
These personalities are considered in various search selectivity thresholds, along with multiple dynamic evaluation score adjustments.
Q-Learning
A learning technique derived from Q-learning, worked out and introduced by Kelly Kinyama [8] [9] and also employed in BrainLearn 9.0 [10], was applied in ShashChess since version 12.0 [11]. After the end of a decisive game in selfplay with appropriate search depth, the list of moves (ml) and associated scores is merged into the learn table from end to start, replacements preferring depth and score, the score of timestep t adjusted as weighted average with the future reward of timestep t+1, using a learning rate α of 0.5 and a discount factor γ of 0.99 [12]:
for (t = ml.size() - 2; t >= 0; t--) {
ml[t].score = (1-α)*ml[t].score + α*γ*ml[t+1].score;
insertIntoOrUpdateLearningTable( ml[t] );
}
Forum Posts
- ShashChess by Andrea Manzo, CCC, July 28, 2018
- Re: ShashChess (11.0) by Andrea Manzo, CCC, March 06, 2020
- Re: ShashChess (12.0) by Andrea Manzo, CCC, June 28, 2020
- Re: ShashChess (15.0) by Andrea Manzo, CCC, October 03, 2020
- Re: ShashChess (17.1) by Andrea Manzo, CCC, June 01, 2021
- Build ShashChess for Android by Andrea Manzo, CCC, August 01, 2018
- ShashChess 12.0 by Andrea Manzo, FishCooking, June 28, 2020
- A new reinforcement learning implementation of Q learning algorithm for alphabeta engines to automatically tune the evaluation of chess positions by Kelly Kinyama, FishCooking, June 29, 2020
- ShashChess NNUE 1.0 by Andrea Manzo, FishCooking, July 25, 2020
- Shashchess which executable to use by Andrew Bernasrd, CCC, January 23, 2021
External Links
- GitHub - amchess/ShashChess: A try to implement Alexander Shashin's theory on a Stockfish's derived chess engine
- ShashChess 11.0 64-bit in CCRL 40/15
- ShashChess 15.0 64-bit in CCRL 40/15
References
- ↑ Welcome to BS Chess
- ↑ Alexander Shashin (2013). Best Play: A New Method for Discovering the Strongest Move. Mongoose Press, Amazon
- ↑ Review: Best Play | ChessVibes by Arne Moll, September 05, 2013 (Wayback Machine)
- ↑ ShashChess by Andrea Manzo, CCC, July 28, 2018
- ↑ ShashChess/README.md at master · amchess/ShashChess · GitHub
- ↑ Re: Komodo MCTS by Mark Lefler, CCC, June 12, 2019 » Komodo MCTS
- ↑ ShashChess/search.cpp at master · amchess/ShashChess · GitHub
- ↑ Re: Self-Learning stockfish upgraded by Kelly Kinyama, FishCooking, May 28, 2019
- ↑ A new reinforcement learning implementation of Q learning algorithm for alphabeta engines to automatically tune the evaluation of chess positions by Kelly Kinyama, FishCooking, June 29, 2020
- ↑ Release BrainLearn 9.0 · amchess/BrainLearn · GitHub
- ↑ ShashChess 12.0 by Andrea Manzo, FishCooking, June 28, 2020
- ↑ ShashChess/search.cpp at master · amchess/ShashChess · GitHub
