Jonathan Baxter - Chess Programming Wiki

Home * People * Jonathan Baxter

Jonathan Baxter ¹

Jonathan Baxter,
an Australian computer scientist, entrepreneur, CEO and co-founder of the Web crawling company Panscient ¹ ², and before quantitative researcher at Two Sigma Investments, a New York City based hedge fund, and distinguished research scientist at WhizBang! Labs, Pittsburgh, Pennsylvania ³ ⁴ ⁵.

Contents

Computer Chess

While affiliated with the Department of Systems Engineering at Australian National University, Jonathan Baxter co-authored the TD-learning chess program KnightCap ⁶ and further wrote his own engine TDChess based on KnightCap ⁷, which won the NC3 1999 Australasian National Computer Chess Championship ⁸. After the AlphaZero incident in December 2017, Jonathan Baxter contributed a Monte-Carlo Tree Search wrapper for Stockfish ⁹.

Jonathan Baxter, Andrew Tridgell, Lex Weaver (1997). Knightcap: A chess program that learns by combining td(λ) with minimax search. 15th International Conference on Machine Learning, pdf via citeseerX
Jonathan Baxter, Andrew Tridgell, Lex Weaver (1998). Experiments in Parameter Learning Using Temporal Differences. ICCA Journal, Vol. 21, No. 2
Jonathan Baxter, Andrew Tridgell, Lex Weaver (1999). TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search. Australian Journal of Intelligent Information Processing Systems, Vol. 5 No. 1, arXiv:cs/9901001
Jonathan Baxter, Andrew Tridgell, Lex Weaver (1999). KnightCap: A chess program that learns by combining TD(lambda) with game-tree search. arXiv:cs/9901002

Jonathan Baxter (2011). A Model of Inductive Bias Learning. arXiv:1106.0245 ¹¹
Jonathan Baxter, Peter Bartlett (2011). Infinite-Horizon Policy-Gradient Estimation. arXiv:1106.0665
Peter Bartlett, Jonathan Baxter, Lex Weaver (2011). Experiments with Infinite-Horizon, Policy-Gradient Estimation. arXiv:1106.0666