Online Markov Decision Processes

References

• Auer P., Cesa-Bianchi N., Gentile C. Adaptive and self-confident on-line learning algorithms. J. Comput. System Sci. (2002) 64:48–75Crossref, Google Scholar
• Bertsekas D. P., Tsitsiklis J. N.Neuro-Dynamic Programming (1996) (Athena Scientific, Belmont, MA) Google Scholar
• Blum A., Kalai A. Universal portfolios with and without transaction costs. Machine Learning (1999) 35:193–205Crossref, Google Scholar
• Borodin A., El-Yaniv R.Online Computation and Competitive Analysis (1998) (Cambridge University Press, Cambridge, UK) Google Scholar
• Cesa-Bianchi N., Freund Y., Helmbold D. P., Haussler D., Schapire R. E., Warmuth M. K. How to use expert advice. J. ACM (1997) 44(3):427–485Crossref, Google Scholar
• de Farias D. P., Megiddo N. Combining expert advice in reactive environments. J. ACM (2006) 53(5):762–799Crossref, Google Scholar
• Hannan J., Dresher M., Tucker A. W., Wolde P. Approximation to Bayes risk in repeated play. Contributions to the Theory of Games, III (1957) (Princeton University Press, Princeton, NJ) 97–139Google Scholar
• Helmbold D. P., Schapire R. E., Singer Y., Warmuth M. K. On-line portfolio selection using multiplicative updates. Math. Finance (1998) 8(4):325–347Crossref, Google Scholar
• Kakade S. M. On the sample complexity of reinforcement learning. (2003) . Ph.D. thesis, University College London, LondonGoogle Scholar
• Kalai A., Vempala S. Efficient algorithms for on-line optimization. J. Comput. System Sci. (2005) 71(3):291–307Crossref, Google Scholar
• Kearns M., Singh S. Near-optimal reinforcement learning in polynomial time. Machine Learning (2002) 49(2–3):209–232Crossref, Google Scholar
• Kivinen J., Warmuth M. Additive versus exponentiated gradient updates for linear prediction. J. Inform. Comput. (1997) 132(1):1–64Crossref, Google Scholar
• Littlestone N., Warmuth M. K. The weighted majority algorithm. Inform. Comput. (1994) 108(2):212–261Crossref, Google Scholar
• McMahan H. Planning in the presence of cost functions controlled by an adversary. Proc. 20th Internat. Conf. Machine Learning (ICML) (2003) Washington, DC:536–543Google Scholar
• McMahan H., Gordon G., Blum A. Personal communication. (2003) Google Scholar
• Nilim A., El Ghaoui L. Robust solutions to Markov decision problems with uncertain transition matrices. Oper. Res. (2005) 53:780–798Link, Google Scholar
• Puterman M.Markov Decision Processes (1994) (Wiley-Interscience, New York) Crossref, Google Scholar
• Sutton R., Barto A.Reinforcement Learning. An Introduction (1998) (MIT Press, Cambridge, MA) Crossref, Google Scholar
• Tsitsiklis J. N. NP-hardness of checking the unichain condition in average cost MDPs. Oper. Res. Lett. (2007) 35(3):319–323Crossref, Google Scholar
• Yu J. Y., Mannor S., Shimkin N. Markov decision processes with arbitrary reward processes. Math. Oper. Res. (2009) 34(3):737–757Link, Google Scholar