@article{kobayashiNN2022,
  author = {Taisuke Kobayashi},
  title = {Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization},
  journal = {Neural Networks},
  year = {2022},
  volume = {152},
  pages = {169--180},
  url = {https://arxiv.org/abs/2105.12991},
  doi = {10.1016/j.neunet.2022.04.021},
}

%RL for washing machine

{"_id":"njc9ZheDpQBnyT4gK","bibbaseid":"kobayashi-optimisticreinforcementlearningbyforwardkullbackleiblerdivergenceoptimization-2022","author_short":["Kobayashi, T."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Taisuke"],"propositions":[],"lastnames":["Kobayashi"],"suffixes":[]}],"title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","journal":"Neural Networks","year":"2022","volume":"152","pages":"169–180","url":"https://arxiv.org/abs/2105.12991","doi":"10.1016/j.neunet.2022.04.021","bibtex":"@article{kobayashiNN2022,\n author = {Taisuke Kobayashi},\n title = {Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization},\n journal = {Neural Networks},\n year = {2022},\n volume = {152},\n pages = {169--180},\n url = {https://arxiv.org/abs/2105.12991},\n doi = {10.1016/j.neunet.2022.04.021},\n}\n\n%RL for washing machine\n","author_short":["Kobayashi, T."],"key":"kobayashiNN2022","id":"kobayashiNN2022","bibbaseid":"kobayashi-optimisticreinforcementlearningbyforwardkullbackleiblerdivergenceoptimization-2022","role":"author","urls":{"Paper":"https://arxiv.org/abs/2105.12991"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://www.dropbox.com/s/ebs0utssp5unpnm/publish.bib?dl=1","dataSources":["Fdi7RLbmsFp46nnDK"],"keywords":[],"search_terms":["optimistic","reinforcement","learning","forward","kullback","leibler","divergence","optimization","kobayashi"],"title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","year":2022}