Difference between revisions of "Joel Veness"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Joel Veness''' FILE:joelveness.jpg|border|right|thumb|link=http://jveness.info/about_me/default.html| Joel Veness <ref>[http://jveness....") |
GerdIsenberg (talk | contribs) |
||
| Line 4: | Line 4: | ||
'''Joel Veness''',<br/> | '''Joel Veness''',<br/> | ||
| − | an Australian games programmer, mathematician and computer scientist with a Ph.D. from [https://en.wikipedia.org/wiki/University_of_New_South_Wales University of New South Wales] (UNSW). He spent two years at the [[University of Alberta]] as a postdoc under [[ | + | an Australian games programmer, mathematician and computer scientist with a Ph.D. from [https://en.wikipedia.org/wiki/University_of_New_South_Wales University of New South Wales] (UNSW). He spent two years at the [[University of Alberta]] as a postdoc under [[Michael Bowling]], and now works in the UK as research scientist at [[Google]] [[DeepMind]] <ref>[http://jveness.info/about_me/default.html Joel Veness - About]</ref>. |
Joel is author of the chess engine [[Bodo]] <ref>[https://www.stmintz.com/ccc/index.php?id=437038 BODO new OZ champion] by [[Ross Boyd]], [[CCC]], July 17, 2005</ref>, written in [[C]] and later [[Cpp|C++]] <ref>[http://users.cecs.anu.edu.au/%7Eshaun/chess/NC32006_-_List_of_Entries.html 2006 National Computer Chess Championships - List of Entries]</ref>. Joel Veness’ chess program [[Meep]] based on Bodo is one of the first master-level programs with an evaluation function that was learned entirely from self-play, by [[Meep#BootStrap|bootstrapping]] from deep searches <ref>[[Joel Veness]], [[David Silver]], [[William Uther]], [[Alan Blair]] ('''2009'''). ''[http://papers.nips.cc/paper/3722-bootstrapping-from-game-tree-search Bootstrapping from Game Tree Search]''. [http://jveness.info/publications/nips2009%20-%20bootstrapping%20from%20game%20tree%20search.pdf pdf], [http://videolectures.net/nips09_veness_bfg/ video presentation]</ref> . | Joel is author of the chess engine [[Bodo]] <ref>[https://www.stmintz.com/ccc/index.php?id=437038 BODO new OZ champion] by [[Ross Boyd]], [[CCC]], July 17, 2005</ref>, written in [[C]] and later [[Cpp|C++]] <ref>[http://users.cecs.anu.edu.au/%7Eshaun/chess/NC32006_-_List_of_Entries.html 2006 National Computer Chess Championships - List of Entries]</ref>. Joel Veness’ chess program [[Meep]] based on Bodo is one of the first master-level programs with an evaluation function that was learned entirely from self-play, by [[Meep#BootStrap|bootstrapping]] from deep searches <ref>[[Joel Veness]], [[David Silver]], [[William Uther]], [[Alan Blair]] ('''2009'''). ''[http://papers.nips.cc/paper/3722-bootstrapping-from-game-tree-search Bootstrapping from Game Tree Search]''. [http://jveness.info/publications/nips2009%20-%20bootstrapping%20from%20game%20tree%20search.pdf pdf], [http://videolectures.net/nips09_veness_bfg/ video presentation]</ref> . | ||
| Line 18: | Line 18: | ||
* [[Joel Veness]], [[Kee Siong Ng]], [[Marcus Hutter]], [[David Silver]] ('''2010'''). ''Reinforcement Learning via AIXI Approximation''. Association for the Advancement of Artificial Intelligence (AAAI), [http://jveness.info/publications/veness_rl_via_aixi_approx.pdf pdf] | * [[Joel Veness]], [[Kee Siong Ng]], [[Marcus Hutter]], [[David Silver]] ('''2010'''). ''Reinforcement Learning via AIXI Approximation''. Association for the Advancement of Artificial Intelligence (AAAI), [http://jveness.info/publications/veness_rl_via_aixi_approx.pdf pdf] | ||
* [[Joel Veness]] ('''2011'''). ''Approximate Universal Artificial Intelligence and Self-Play Learning for Games''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_New_South_Wales University of New South Wales], supervisors: [[Kee Siong Ng]], [[Marcus Hutter]], [[Alan Blair]], [[William Uther]], [[John Lloyd]]; [http://jveness.info/publications/veness_phd_thesis_final.pdf pdf] | * [[Joel Veness]] ('''2011'''). ''Approximate Universal Artificial Intelligence and Self-Play Learning for Games''. Ph.D. thesis, [https://en.wikipedia.org/wiki/University_of_New_South_Wales University of New South Wales], supervisors: [[Kee Siong Ng]], [[Marcus Hutter]], [[Alan Blair]], [[William Uther]], [[John Lloyd]]; [http://jveness.info/publications/veness_phd_thesis_final.pdf pdf] | ||
| − | * [[Joel Veness]], [[Marc Lanctot]], [[ | + | * [[Joel Veness]], [[Marc Lanctot]], [[Michael Bowling]] ('''2011'''). ''Variance Reduction in Monte-Carlo Tree Search''. [http://papers.nips.cc/book/advances-in-neural-information-processing-systems-24-2011 NIPS], [http://papers.nips.cc/paper/4288-variance-reduction-in-monte-carlo-tree-search.pdf pdf] |
* [[Marc Lanctot]], [[Abdallah Saffidine]], [[Joel Veness]], [[Christopher Archibald]] ('''2012'''). ''Sparse Sampling for Adversarial Games''. [[ECAI CGW 2012]] | * [[Marc Lanctot]], [[Abdallah Saffidine]], [[Joel Veness]], [[Christopher Archibald]] ('''2012'''). ''Sparse Sampling for Adversarial Games''. [[ECAI CGW 2012]] | ||
* [[Marc Lanctot]], [[Abdallah Saffidine]], [[Joel Veness]], [[Christopher Archibald]], [[Mark Winands]] ('''2013'''). ''Monte Carlo *-Minimax Search''. [[Conferences#IJCAI|IJCAI 2013]] | * [[Marc Lanctot]], [[Abdallah Saffidine]], [[Joel Veness]], [[Christopher Archibald]], [[Mark Winands]] ('''2013'''). ''Monte Carlo *-Minimax Search''. [[Conferences#IJCAI|IJCAI 2013]] | ||
Revision as of 08:41, 4 June 2018
Joel Veness [1]
Joel Veness,
an Australian games programmer, mathematician and computer scientist with a Ph.D. from University of New South Wales (UNSW). He spent two years at the University of Alberta as a postdoc under Michael Bowling, and now works in the UK as research scientist at Google DeepMind [2].
Joel is author of the chess engine Bodo [3], written in C and later C++ [4]. Joel Veness’ chess program Meep based on Bodo is one of the first master-level programs with an evaluation function that was learned entirely from self-play, by bootstrapping from deep searches [5] .
Contents
Selected Publications
2006 ...
- Joel Veness (2006). Expectimax Enhancements for Stochastic Game Players. BSc-Thesis, pdf
- Joel Veness, Alan Blair (2007). Effective Use of Transposition Tables in Stochastic Game Tree Search. IEEE Symposium on Computational Intelligence and Games, pdf
- Joel Veness, David Silver, William Uther, Alan Blair (2009). Bootstrapping from Game Tree Search. pdf [8], video presentation
- Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver (2009). A Monte Carlo AIXI Approximation, pdf
2010 ...
- Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver (2010). Reinforcement Learning via AIXI Approximation. Association for the Advancement of Artificial Intelligence (AAAI), pdf
- Joel Veness (2011). Approximate Universal Artificial Intelligence and Self-Play Learning for Games. Ph.D. thesis, University of New South Wales, supervisors: Kee Siong Ng, Marcus Hutter, Alan Blair, William Uther, John Lloyd; pdf
- Joel Veness, Marc Lanctot, Michael Bowling (2011). Variance Reduction in Monte-Carlo Tree Search. NIPS, pdf
- Marc Lanctot, Abdallah Saffidine, Joel Veness, Christopher Archibald (2012). Sparse Sampling for Adversarial Games. ECAI CGW 2012
- Marc Lanctot, Abdallah Saffidine, Joel Veness, Christopher Archibald, Mark Winands (2013). Monte Carlo *-Minimax Search. IJCAI 2013
2015 ...
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis (2015). Human-level control through deep reinforcement learning. Nature, Vol. 518
- James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell (2016). Overcoming catastrophic forgetting in neural networks. arXiv:1612.00796
Forum Posts
- quiescent nodes, and history heuristic... by Joel Veness, CCC, January 30, 2003 » Quiescent Node, History Heuristic
- Your program is a ... by Joel Veness, CCC, October 29, 2003
- Re: CCT6: Rybka /Bodo ??? by Joel Veness, CCC, January 26, 2004 » CCT6, Rybka, Bodo
- Bodo @ CCT6....day 1.... by Joel Veness, CCC, February 03, 2004
- Re: BODO new OZ champion by Joel Veness, CCC, July 17, 2005 » NC3 2005
External Links
- Homepage of Joel Veness
- Joel Veness from Microsoft Academic Search
- Veness, Joel from computer-go.info
- Bootstrapping from Game Tree Search, video presentation by Joel Veness, from VideoLectures - exchange ideas & share knowledge, December 2009
- Enabling Continual Learning in Neural Networks by James Kirkpatrick, Joel Veness et al., DeepMind, March 13, 2017 » Deep Learning, Neural Networks
References
- ↑ Joel Veness - About
- ↑ Joel Veness - About
- ↑ BODO new OZ champion by Ross Boyd, CCC, July 17, 2005
- ↑ 2006 National Computer Chess Championships - List of Entries
- ↑ Joel Veness, David Silver, William Uther, Alan Blair (2009). Bootstrapping from Game Tree Search. pdf, video presentation
- ↑ Joel Veness - Publications
- ↑ Joel Veness from Microsoft Academic Search
- ↑ A paper about parameter tuning by Rémi Coulom, CCC, January 12, 2010
