Alexander L. Strehl, Lihong Li, Eric Wiewiora, John Langford, Michael L. Littman. PAC model-free reinforcement learning. In William W. Cohen, Andrew Moore, editors, Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006. Volume 148 of ACM International Conference Proceeding Series, pages 881-888, ACM, 2006. [doi]
@inproceedings{StrehlLWLL06, title = {PAC model-free reinforcement learning}, author = {Alexander L. Strehl and Lihong Li and Eric Wiewiora and John Langford and Michael L. Littman}, year = {2006}, doi = {10.1145/1143844.1143955}, url = {http://doi.acm.org/10.1145/1143844.1143955}, tags = {meta-model, Meta-Environment}, researchr = {https://researchr.org/publication/StrehlLWLL06}, cites = {0}, citedby = {0}, pages = {881-888}, booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006}, editor = {William W. Cohen and Andrew Moore}, volume = {148}, series = {ACM International Conference Proceeding Series}, publisher = {ACM}, isbn = {1-59593-383-2}, }