@Article{	  dblp3550366,
  title		= {Using Expectation-Maximization for Reinforcement
		  Learning},
  author	= {Peter Dayan and Geoffrey E. Hinton},
  author_short	= {Dayan, P. and Hinton, G. E.},
  bibtype	= {article},
  type		= {article},
  year		= {1997},
  key		= {dblp3550366},
  id		= {dblp3550366},
  biburl	= {http://www.dblp.org/rec/bibtex/journals/neco/DayanH97},
  url_link	= {http://dx.doi.org/10.1162/neco.1997.9.2.271},
  journal	= {Neural Computation (NECO)},
  pages		= {271-278},
  number	= {2},
  volume	= {9},
  text		= {Neural Computation (NECO) 9(2):271-278 (1997)},
  url_abstract	= {absps/dh97.html},
  url_psgz	= {absps/dh97.ps.gz},
  url_pdf	= {absps/dh97.pdf}
}

{"_id":{"_str":"534259580e946d920a0009fb"},"__v":7,"authorIDs":["2ACfCTBEv4pRPLwBb","4DQrsTmafKuPbvKom","5457dd852abc8e9f3700082c","5de76c4f179cbdde01000135","5de7b92fbc280fdf01000192","5de7e861c8f9f6df01000188","5de7ff309b61e8de0100005f","5de917d35d589edf01000025","5de93bf8b8c3f8de010000a3","5de95819d574c6de010000d5","5de96615d574c6de010001ab","5de9faf7fac96fde01000039","5dea1112fac96fde01000194","5deb75f49e04d1df010000c8","5deb8542b62591df0100002d","5deb946fb62591df010000ef","5decb37d93ac84df01000108","5dece9a3619535de010000f9","5dee20da584fb4df0100023f","5dee5ebb773914de01000077","5dee6b12773914de0100015a","5deea5af0ceb4cdf01000193","5deee4cc66e59ade01000133","5def23c6e83f7dde0100003c","5def2e39e83f7dde010000a6","5def601cfe2024de01000084","5defdd35090769df01000181","5df0938cf651f5df01000056","5df0980df651f5df010000a2","5df0c74096fa76de01000024","5df0eda045b054df010000fb","5df2008fe4cb4ede01000035","5df2583563aac8df010000ad","5df25ae963aac8df010000dd","5df28978cf8320de0100001f","5df3756223fb6fdf010000fe","5df38d112b1f8ade01000086","5df3f9cad1756cdf01000039","5df4ca0755b997de0100009a","5df4cd8055b997de010000c2","5df53e56fd245cde01000125","5df60b78a37a40df01000156","5df62fce38e915de0100004b","5df6491ddf30fcdf0100003d","5df67503797ba9de01000104","5df6983872bbd4df01000160","5df6b0e031a37ade01000178","5df789d35c8a36df010000f7","5df7c23392a8e4df010000da","5df7dafbdc100cde010000e1","5df7e65edc100cde010001c6","5df89d4010b1d1de01000088","5df8b0cee6b510df01000021","5df93745d04b27df01000185","5df9d77138a7afde01000084","5dfa483ced5baede0100011b","5dfa67a37d1403df01000123","5dfbc3f34705b7de01000022","5dfcc5cc7a3608de0100004f","5dfe49bfbfbabdde01000004","5e1dc9478d71ddde0100015d","5e29d9d0888177df0100011e","5e48c117f1ed39de0100008d","5e555c0ee89e5fde010000e6","5e55fa1c819fabdf0100003a","5e5b04db6e568ade0100001f","5hGMdsfN7BrXW6K8T","5vmPz2jJcYQdtZPiZ","6yoSqPPyPrLdz8e5Q","BYkXaBeGZENiggkom","Bm98SYMoSNDbYwKGj","EsmZfHTQHAoi4zrJ2","N6cuxqTfG9ybhWDqZ","PXRdnhZs2CXY9NLhX","Q7zrKooGeSy8NTBjC","QxWxCp32GcmNqJ9K2","WnMtdN4pbnNcAtJ9C","e3ZEg6YfZmhHyjxdZ","exw99o2vqr9d3BXtB","fnGMsMDrpkcjCLZ5X","gN5Lfqjgx8P4c7HJT","gxtJ9RRRnpW2hQdtv","hCHC3WLvySqxwH4eZ","jN4BRAzEpDg6bmHmM","mBpuinLcpSzpxcFaz","n3Tju5NZ6trek5XEM","n3hXojCsQTaqGTPyY","ovEhxZqGLG9hGfrun","rnZ6cT67qkowNdLgz","u6Fai3nvyHwLKZpPn","vcz5Swk9goZXRki2G","x9kDqsoXq57J2bEu5","xmZk6XEacSsFbo2Sy","xufS6EqKGDqRQs47H"],"author_short":["Dayan, P.","Hinton, G. E."],"bibbaseid":"dayan-hinton-usingexpectationmaximizationforreinforcementlearning-1997","bibdata":{"bibtype":"article","type":"article","title":"Using Expectation-Maximization for Reinforcement Learning","author":[{"firstnames":["Peter"],"propositions":[],"lastnames":["Dayan"],"suffixes":[]},{"firstnames":["Geoffrey","E."],"propositions":[],"lastnames":["Hinton"],"suffixes":[]}],"author_short":["Dayan, P.","Hinton, G. E."],"year":"1997","key":"dblp3550366","id":"dblp3550366","biburl":"http://www.dblp.org/rec/bibtex/journals/neco/DayanH97","url_link":"http://dx.doi.org/10.1162/neco.1997.9.2.271","journal":"Neural Computation (NECO)","pages":"271-278","number":"2","volume":"9","text":"Neural Computation (NECO) 9(2):271-278 (1997)","url_abstract":"absps/dh97.html","url_psgz":"absps/dh97.ps.gz","url_pdf":"absps/dh97.pdf","bibtex":"@Article{\t dblp3550366,\n title\t\t= {Using Expectation-Maximization for Reinforcement\n\t\t Learning},\n author\t= {Peter Dayan and Geoffrey E. Hinton},\n author_short\t= {Dayan, P. and Hinton, G. E.},\n bibtype\t= {article},\n type\t\t= {article},\n year\t\t= {1997},\n key\t\t= {dblp3550366},\n id\t\t= {dblp3550366},\n biburl\t= {http://www.dblp.org/rec/bibtex/journals/neco/DayanH97},\n url_link\t= {http://dx.doi.org/10.1162/neco.1997.9.2.271},\n journal\t= {Neural Computation (NECO)},\n pages\t\t= {271-278},\n number\t= {2},\n volume\t= {9},\n text\t\t= {Neural Computation (NECO) 9(2):271-278 (1997)},\n url_abstract\t= {absps/dh97.html},\n url_psgz\t= {absps/dh97.ps.gz},\n url_pdf\t= {absps/dh97.pdf}\n}\n\n","bibbaseid":"dayan-hinton-usingexpectationmaximizationforreinforcementlearning-1997","role":"author","urls":{" link":"http://dx.doi.org/10.1162/neco.1997.9.2.271"," abstract":"http://www.cs.toronto.edu/~fritz/absps/dh97.html"," psgz":"http://www.cs.toronto.edu/~fritz/absps/dh97.ps.gz"," pdf":"http://www.cs.toronto.edu/~fritz/absps/dh97.pdf"},"metadata":{"authorlinks":{"hinton, g":"https://bibbase.org/show?bib=www.cs.toronto.edu/~fritz/master3.bib&theme=side"}}},"bibtype":"article","biburl":"http://www.cs.toronto.edu/~fritz/master3.bib","downloads":0,"keywords":[],"search_terms":["using","expectation","maximization","reinforcement","learning","dayan","hinton"],"title":"Using Expectation-Maximization for Reinforcement Learning","year":1997,"dataSources":["avdRdTCKoXoyxo2tQ","GtChgCdrAm62yoP3L"]}