Changes

an experimental chess engine as subject of research on [[Learning|machine learning]] techniques and [[Automated Tuning|automated tuning]], written by [[Joel Veness]], supported by [[David Silver]], [[William Uther]], and [[Alan Blair]], as elaborated in their 2009 research paper this page is based on <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]</ref> , and in Joel Veness' Ph.D. thesis <ref>[[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]</ref> . Meep is based on the [[UCI]] compliant tournament chess engine [[Bodo]], where the hand-crafted [[Evaluation Function|evaluation function]] is replaced by a weighted [https://en.wikipedia.org/wiki/Linear_combination linear combination] of 1812 features. Given a position s, a [https://en.wikipedia.org/wiki/Feature_vector feature vector] Φ(s) can be constructed from the 1812 numeric values of each feature. The majority of these features are binary. Φ(s) is typically sparse, with approximately 100 features active in any given position. Five wellknown, chess specific feature construction concepts, [[Material|material]], [[Piece-Square Tables|piece square tables]], [[Pawn Structure|pawn structure]], [[Mobility|mobility]] and [[King Safety|king safety]] were used to generate the 1812 distinct features. In a training mode with various search frameworks, Meep learns from self-play to adjust the weights of its evaluation function towards the value of the deep search. A tournament mode is later used to verify the [[Playing Strength|strength]] of a trained weight configuration.

In contrast to [[Temporal Difference Learning|temporal difference methods]] such as [[Temporal Difference Learning#TDLeaf|TD-Leaf]] <ref>[[Jonathan Baxter]], [[Andrew Tridgell]], [[Lex Weaver]] ('''1998'''). ''TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search''. [https://www.chatbots.org/journal/australian_journal_of_intelligent_information_processing_systems/ Australian Journal of Intelligent Information Processing Systems], Vol. 5 No. 1, [http://arxiv.org/abs/cs/9901001 arXiv:cs/9901001]</ref> as used in [[KnightCap]] <ref>[[Jonathan Baxter]], [[Andrew Tridgell]], [[Lex Weaver]] ('''1998''') ''Knightcap: A chess program that learns by combining td(λ) with game-tree search''. Proceedings of the 15th International Conference on Machine Learning</ref> , where the target search is performed at subsequent time-steps, after a real move and response have been played, Meep performs various [https://en.wikipedia.org/wiki/Bootstrap_aggregating bootstrapping] techniques during training, dubbed '''RootStrap''' and '''TreeStrap''', to adjust the weights at every time-step inside either a [[Minimax|minimax]] or [[Alpha-Beta|alpha-beta]] search. With the heuristic evaluation function as linear combination of

* [[István Szita]] ('''2012'''). ''[http://link.springer.com/chapter/10.1007%2F978-3-642-27645-3_17 Reinforcement Learning in Games]''. in [[Marco Wiering]], [http://martijnvanotterlo.nl/ Martijn Van Otterlo] (eds.). ''[https://scholar.google.com/citations?view_op=view_citation&hl=en&user=xVas0I8AAAAJ&citation_for_view=xVas0I8AAAAJ:abG-DnoFyZgC Reinforcement learning: State-of-the-art]''. [http://link.springer.com/book/10.1007/978-3-642-27645-3 Adaptation, Learning, and Optimization, Vol. 12], [https://en.wikipedia.org/wiki/Springer_Science%2BBusiness_Media Springer]

* [[Videos#VolkerKriegel:Category:Volker Kriegel|Volker Kriegel]] - Three Or Two In One, [http://www.discogs.com/Volker-Kriegel-Lift/release/726875 Lift!], 1973, [https://en.wikipedia.org/wiki/YouTube YouTube] Video: feat: [[Videos#EberhardWeber:Category:Eberhard Weber|Eberhard Weber]], [[Videos#JohnMarshall:Category:John Marshall|John Marshall]], [https://en.wikipedia.org/wiki/Stan_Sulzmann Stan Sulzmann], [https://en.wikipedia.org/wiki/John_Taylor_%28jazz%29 John Taylor], [https://de.wikipedia.org/wiki/Cees_See Cees See], [[Videos#ZbigniewSeifert:Category:Zbigniew Seifert|Zbigniew Seifert]]: {{#evu:https://www.youtube.com/watch?v=neBBmEAHQoQNmiEyjWgkRc|alignment=left|valignment=top}}