Difference between revisions of "Jonathan Baxter"

From Chessprogramming wiki
Jump to: navigation, search
Line 21: Line 21:
 
* [[Jonathan Baxter]], [[Peter Bartlett]] ('''2000'''). ''Reinforcement Learning on POMDPs via Direct Gradient Ascent''. [http://dblp.uni-trier.de/db/conf/icml/icml2000.html ICML 2000], [https://pdfs.semanticscholar.org/b874/98f0879d312c308889135203b17069aa0486.pdf pdf]
 
* [[Jonathan Baxter]], [[Peter Bartlett]] ('''2000'''). ''Reinforcement Learning on POMDPs via Direct Gradient Ascent''. [http://dblp.uni-trier.de/db/conf/icml/icml2000.html ICML 2000], [https://pdfs.semanticscholar.org/b874/98f0879d312c308889135203b17069aa0486.pdf pdf]
 
* [[Jonathan Baxter]], [[Peter Bartlett]] ('''2001'''). ''Infinite-Horizon Policy-Gradient Estimation''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research Journal of Artificial Intelligence Research] 15, [http://neuro.bstu.by/ai/To-dom/My_research/Papers-2.0/STDP/Reinforcement-L/A/Refs/baxter01a.pdf pdf]
 
* [[Jonathan Baxter]], [[Peter Bartlett]] ('''2001'''). ''Infinite-Horizon Policy-Gradient Estimation''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research Journal of Artificial Intelligence Research] 15, [http://neuro.bstu.by/ai/To-dom/My_research/Papers-2.0/STDP/Reinforcement-L/A/Refs/baxter01a.pdf pdf]
 +
* [[Lex Weaver]], [[Jonathan Baxter]] ('''2001'''). ''STD (λ): learning state differences with TD (λ)''. [http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.7737 CiteSeerX]
 
* [https://www.linkedin.com/in/dougaberdeen/ Douglas Aberdeen], [[Jonathan Baxter]] ('''2001'''). ''[https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.549 Emmerald: a fast matrix-matrix multiply using Intel's SSE instructions]''. [https://onlinelibrary.wiley.com/journal/15320634 Concurrency and Computation: Practice and Experience], Vol. 13, No. 2
 
* [https://www.linkedin.com/in/dougaberdeen/ Douglas Aberdeen], [[Jonathan Baxter]] ('''2001'''). ''[https://onlinelibrary.wiley.com/doi/abs/10.1002/cpe.549 Emmerald: a fast matrix-matrix multiply using Intel's SSE instructions]''. [https://onlinelibrary.wiley.com/journal/15320634 Concurrency and Computation: Practice and Experience], Vol. 13, No. 2
 
==2010 ...==
 
==2010 ...==

Revision as of 12:25, 23 June 2018

Home * People * Jonathan Baxter

Jonathan Baxter [1]

Jonathan Baxter,
an Australian computer scientist, entrepreneur, CEO and co-founder of the Web crawling company Panscient [2] [3], and before quantitative researcher at Two Sigma Investments, a New York City based hedge fund, and distinguished research scientist at WhizBang! Labs, Pittsburgh, Pennsylvania [4] [5] [6].

Computer Chess

While affiliated with the Department of Systems Engineering at Australian National University, Jonathan Baxter co-authored the TD-learning chess program KnightCap [7] and further wrote his own engine TDChess based on KnightCap [8], which won the NC3 1999 Australasian National Computer Chess Championship [9]. After the AlphaZero incident in December 2017, Jonathan Baxter contributed a Monte-Carlo Tree Search wrapper for Stockfish [10].

Selected Publications

[11]

1997 ...

2000 ...

2010 ...

Forum Posts

1998 ...

2010 ...

External Links

References

Up one level