Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations. Böhmer, W., Springenberg, J. T., Boedecker, J., Riedmiller, M. A., & Obermayer, K. KI, 29(4):353-362, 2015.
Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations. [link]Link  Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations. [link]Paper  bibtex   
@article{journals/ki/BohmerSBRO15,
  added-at = {2015-10-29T00:00:00.000+0100},
  author = {Böhmer, Wendelin and Springenberg, Jost Tobias and Boedecker, Joschka and Riedmiller, Martin A. and Obermayer, Klaus},
  biburl = {http://www.bibsonomy.org/bibtex/27d0df52f3aed57b6774de9c7eb7391be/dblp},
  ee = {http://dx.doi.org/10.1007/s13218-015-0356-1},
  interhash = {73e9bb4990c20a3043dab9b55ab8d6d9},
  intrahash = {7d0df52f3aed57b6774de9c7eb7391be},
  journal = {KI},
  keywords = {dblp},
  number = 4,
  pages = {353-362},
  timestamp = {2015-10-30T11:34:10.000+0100},
  title = {Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations.},
  url = {http://dblp.uni-trier.de/db/journals/ki/ki29.html#BohmerSBRO15},
  volume = 29,
  year = 2015
}

Downloads: 0