• Om Kshirsagar

One of the biggest domains for Artificial intelligence is the domain of games. The algorithms for chess mostly include various search techniques, chess-specific adaptation, and specially developed algorithms by the experts in chess. Recently Alpha Zero - a recent development has performed exceptionally. AlphaZero is an algorithm based on reinforced learning i.e., a self-learning, observing, and self- rewarding-based algorithm. The program has learned everything it knows by playing- evaluating-rewarding itself. The leading program in chess - stockfish which used alpha-beta search - was one of the strongest. In a 100-game match, AlphaZero defeated StockFish. In this paper, we will compare AlphaZero with Stockfish by looking at the algorithms used, games played, and the decision process of each program.

Artificial Intelligence, reinforcement learning, Monte-Carlo Tree Search, AlphaZero, Deep Mind, StockFish, Computer Chess, neural network, alpha- beta, chess shogi, AlphaZero stockfish

"AlphaZero Vs StockFish – A Review of Chess Engines", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.b451-b457, April-2022, Available :http://www.jetir.org/papers/JETIR2204161.pdf

"AlphaZero Vs StockFish – A Review of Chess Engines", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppb451-b457, April-2022, Available at : http://www.jetir.org/papers/JETIR2204161.pdf