Free energy based policy gradients

Evangelos Theodorou, Jiri Najemnik, Emanuel Todorov. Free energy based policy gradients. In Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013, IEEE Symposium Series on Computational Intelligence (SSCI), 16-19 April 2013, Singapore. pages 124-131, IEEE, 2013. [doi]

@inproceedings{TheodorouNT13,
  title = {Free energy based policy gradients},
  author = {Evangelos Theodorou and Jiri Najemnik and Emanuel Todorov},
  year = {2013},
  doi = {10.1109/ADPRL.2013.6614998},
  url = {http://dx.doi.org/10.1109/ADPRL.2013.6614998},
  researchr = {https://researchr.org/publication/TheodorouNT13},
  cites = {0},
  citedby = {0},
  pages = {124-131},
  booktitle = {Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013, IEEE Symposium Series on Computational Intelligence (SSCI), 16-19 April 2013, Singapore},
  publisher = {IEEE},
  isbn = {978-1-4673-5925-2},
}