Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task

Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task. Sallans, B. & Hinton, G. E. In Proceedings of Neural Information Processing Systems (NIPS), pages 1075-1081, 2000.

Abstract

Psgz

Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task [pdf]

Pdf bibtex

@InProceedings{	  dblp3399788,
  title		= {Using Free Energies to Represent Q-values in a Multiagent
		  Reinforcement Learning Task},
  author	= {Brian Sallans and Geoffrey E. Hinton},
  author_short	= {Sallans, B. and Hinton, G. E.},
  bibtype	= {inproceedings},
  type		= {inproceedings},
  year		= {2000},
  key		= {dblp3399788},
  id		= {dblp3399788},
  biburl	= {http://www.dblp.org/rec/bibtex/conf/nips/SallansH00},
  conference	= {NIPS},
  pages		= {1075-1081},
  text		= {NIPS 2000:1075-1081},
  booktitle	= {Proceedings of Neural Information Processing Systems
		  (NIPS)},
  url_abstract	= {absps/nips00-bs.htm},
  url_psgz	= {absps/nips00-bs.ps.gz},
  url_pdf	= {absps/nips00-bs.pdf}
}

Downloads: 0