%0 Journal Article %1 noauthororeditor %A Nadjahi, Kimia %A Laroche, Romain %A des Combe, Rémi Tachet %D 2019 %K markov-processes reinforcement-learning sampling %T Safe Policy Improvement with Soft Baseline Bootstrapping %U https://ecmlpkdd2019.org/downloads/paper/339.pdf

@article{noauthororeditor, added-at = {2019-09-17T20:06:50.000+0200}, author = {Nadjahi, Kimia and Laroche, Romain and des Combe, Rémi Tachet}, biburl = {https://www.bibsonomy.org/bibtex/24f52cd3cabcac451fe3d4a8235e27ccb/kirk86}, description = {339.pdf}, interhash = {fb824b2bffbaff845bd5d02dc8bafc3d}, intrahash = {4f52cd3cabcac451fe3d4a8235e27ccb}, keywords = {markov-processes reinforcement-learning sampling}, timestamp = {2019-09-17T20:45:17.000+0200}, title = {Safe Policy Improvement with Soft Baseline Bootstrapping}, url = {https://ecmlpkdd2019.org/downloads/paper/339.pdf}, year = 2019 }