Reading List
Recommended Papers
.
Note: .
Foundations of Stochastic Control
- Bertsekas, D. P., and Shreve, S. E. Stochastic Optimal Control: The Discrete-Time Case. Academic Press, 1978. A canonical reference for measurability subtleties in dynamic programming.
- Hernández-Lerma, O., and Lasserre, J. B. Discrete-Time Markov Control Processes. Springer, 1996. Clean treatment of average-cost criteria and existence results.
- Yüksel, S., and Başar, T. Stochastic Networked Control Systems. Birkhäuser, 2013. Information-theoretic perspective on control under communication constraints.
Nonlinear Filtering & Ergodicity
- Van Handel, R. The stability of conditional Markov processes and Markov chains in random environments. Annals of Probability, 37(5):1876–1925, 2009. Foundational result on filter stability under mild assumptions.
- Chigansky, P., Liptser, R., and van Handel, R. Intrinsic methods in filter stability. Handbook of Nonlinear Filtering, Oxford Univ. Press, 2011. Pedagogical survey — good entry point into the area.
- McDonald, C., and Yüksel, S. Exponential filter stability via Dobrushin's coefficient. Electronic Communications in Probability, 25, 2020. A short, sharp account of the Dobrushin contraction technique.
POMDPs & Reinforcement Learning
- Kara, A. D., and Yüksel, S. Near optimality of finite memory feedback policies in partially observed Markov decision processes. Journal of Machine Learning Research, 23, 2022. Finite-window approximations with explicit error bounds.
- Saldi, N., Linder, T., and Yüksel, S. Finite Approximations in Discrete-Time Stochastic Control. Birkhäuser, 2018. Quantization-based approximations with convergence guarantees.
- Singh, S., Jaakkola, T., and Jordan, M. Learning without state-estimation in partially observable Markovian decision processes. ICML, 1994. Classic motivation for finite-memory policies in RL.
Probability & Graph Theory
- Aldous, D., and Fill, J. Reversible Markov Chains and Random Walks on Graphs. Unfinished monograph, 2002. The standard reference for mixing, cover, and hitting times.
- Levin, D., Peres, Y., and Wilmer, E. Markov Chains and Mixing Times. AMS, 2nd ed., 2017. A friendly modern textbook on mixing-time techniques.