A Learning Algorithm for Risk-Sensitive Cost

References

• Abramovich Y. A., Aliprantis C. D.An Invitation to Operator Theory (2002) (American Mathematical Society, Providence, RI) Crossref, Google Scholar
• Bagchi A., Sureshkumar K., Yong J. Dynamic asset management: Risk sensitive criterion with positive factors constraints. Recent Developments in Mathematical Finance (2002) (World Scientific, Hong Kong) 1–11Crossref, Google Scholar
• Balaji S., Meyn S. P. Multiplicative ergodicity and large deviations for an irreducible Markov chain. Stochastic Processes Their Appl. (2000) 90:123–144Crossref, Google Scholar
• Bapat R. B., Raghavan T. E. S.Nonnegative Matrices and Applications (1997) (Cambridge University Press, Cambridge, UK) Crossref, Google Scholar
• Barto A. G., Sutton R. S., Anderson C. Neuron-like elements that can solve difficult learning control problems. IEEE Trans. Systems Man Cybernetics (1983) 13:835–846Google Scholar
• Benaim M., Azéma J., Emery M., Ledoux M., Yor M. Dynamics of stochastic approximation algorithms. Le Séminaire de Probabilités. Springer Lecture Notes in Mathematics (1999) 1709(Springer Verlag, Berlin-Heidelberg) 1–68Crossref, Google Scholar
• Benveniste A., Metivier M., Priouret P.Adaptive Algorithms and Stochastic Approximations (1991) (Springer Verlag, Berlin-Heidelberg) Google Scholar
• Bertsekas D. P., Nedic A. Least squares policy evaluation algorithms with linear function approximation. Discrete Event Dynamical Systems (2003) 13:79–110Crossref, Google Scholar
• Bertsekas D. P., Tsitsiklis J. N.Neurodynamic Programming (1996) (Athena Scientific, Belmont, MA) Google Scholar
• Bertsekas D. P., Borkar V. S., Nedic A., Si J., Barto A. G., Powell W. B., Wunsch D. Improved temporal difference methods with linear function approximation. Handbook of Learning and Approximate Dynamic Programming (2004) (IEEE Press, New York) 235–259Google Scholar
• Bhatia R.Matrix Analysis (1997) (Springer Verlag, New York) Crossref, Google Scholar
• Bielecki T. R., Pliska S. R. Risk sensitive dynamic asset management. Appl. Math. Optim. (1999) 39:337–360Crossref, Google Scholar
• Bielecki T. R., Pliska S. R. Risk sensitive asset management with transaction costs. Finance Stochastics (2000) 4:1–33Crossref, Google Scholar
• Bielecki T. R., Pliska S. R. Economic properties of the risk-sensitive criterion for portfolio management. Rev. Account. Finance (2003) 2:3–17Crossref, Google Scholar
• Borkar V. S. A sensitivity formula for risk-sensitive cost and the actor-critic algorithm. Systems Control Lett. (2001) 44:339–346Crossref, Google Scholar
• Borkar V. S. Q-learning for risk-sensitive control. Math. Oper. Res. (2002) 27:294–311Link, Google Scholar
• Borkar V. S., Meyn S. P. The o.d.e. method for convergence of stochastic approximation and reinforcement learning. SIAM J. Control Optim. (2000) 38:447–469Crossref, Google Scholar
• Borkar V. S., Meyn S. P. Risk-sensitive optimal control for Markov decision processes with monotone costs. Math. Oper. Res. (2002) 27:192–209Link, Google Scholar
• Derevitskii D. P., Fradkov A. L. Two models for analyzing the dynamics of adaptation algorithms. Automation Remote Control (1974) 35:59–67Google Scholar
• Di Masi G. B., Stettner L. On adaptive and multiplicative (controlled) Poisson equations: Approximation and probability. Bonach Center Publications (2006) 72:57–70Crossref, Google Scholar
• Di Masi G. B., Stettner L. Infinite horizon risk sensitive control of discrete time Markov processes under minorization property. SIAM J. Control Optim. (2007) 46:231–252Crossref, Google Scholar
• Golub G. H., Van Loan C. F.Matrix Computations (1996) (Johns Hopkins University Press, Baltimore, MD) Google Scholar
• Hirsch M. W. Convergent activation dynamics in continuous time networks. Neural Networks (1989) 2:331–349Crossref, Google Scholar
• Karatzas I., Shreve S. E.Brownian Motion and Stochastic Calculus (1988) (Springer-Verlag, New York) Crossref, Google Scholar
• Kontoyiannis I., Meyn S. P. Spectral theory and limit theorems for geometrically ergodic Markov processes. Anal. Appl. Probab. (2003) 13:304–362Crossref, Google Scholar
• Kontoyiannis I., Meyn S. P. Large deviations asymptotics and the spectral theory of multiplicatively regular Markov processes. Electronic J. Probab. (2005) 10:61–123Crossref, Google Scholar
• Kushner H. J., Dupuis P.Numerical Methods for Stochastic Control Problems in Continuous Time (2001) 2nd ed.(Springer-Verlag, New York) Crossref, Google Scholar
• Si J., Barto A. G., Powell W. B., Wunsch D.Handbook of Learning and Approximate Dynamic Programming (2004) (IEEE Press, New York) Crossref, Google Scholar
• Stewart G. W.Matrix Algorithms (2001) II(SIAM, Philadelphia) Crossref, Google Scholar
• Sutton R. S., Barto A. G.Reinforcement Learning (1998) (MIT Press, Cambridge, MA) Google Scholar
• Tsitsiklis J. N., Van Roy B. An analysis of temporal-difference learning with function approximation. IEEE Trans. Automatic Control (1997) 42:674–690Crossref, Google Scholar
• Watkins C. J. C. H. Learning from delayed rewards. (1989) . Ph.D. thesis, University of Cambridge, Cambridge, UKGoogle Scholar
• Wilson F. W. Smoothing derivatives of functions and applications. Trans. Amer. Math. Soc. (1969) 139:413–428Crossref, Google Scholar