| Date | Speaker | Title |
|---|---|---|
| 2023-09-15 | Yunus Emre Demirci | Average Cost
Optimality of Partially Observed MDPs: Contraction of
Non-Linear Filters and Existence of Optimal Solutions |
| 2023-09-22 | Liam Cregg |
Finite-Memory Codes for Zero-Delay Coding of Markov Sources |
| 2023-10-06 | Somnath Pradhan |
Robustness of Optimal Control for Diffusions with
Near-Brownian Noise via Rough Paths Theory |
| 2023-10-16 |
irregular seminar: Nicolas Garcia (Princeton) |
The Moran Model from Mathematical Biology, and its
Limit Fischer-Wright Diffusion |
| 2023-10-20 |
Serdar Yüksel |
Existence of Optimal Control Policies under Full, Partial, and Decentralized Information in Continuous-Time and Discrete-Time |
| 2023-10-27 |
Sina Sanjari |
Large
Continuous-Time Stochastic Exchangeable Teams and
Their Mean-Field Limit |
| 2023-11-03 |
Zachary Selk |
A Comparison of
Skorokhod and Russo-Vallois Anticipative Integrals
in Insider Trading |
| 2023-11-10 | Omar Mrani-Zentar | Decentralized
Stochastic Control with Delayed and Periodic
Information Sharing: Structural Results and the
Feller Property |
| 2023-11-17 |
Omar Mrani-Zentar | Decentralized Stochastic Control with Delayed and Periodic Information Sharing: Structural Results and the Feller Property |
| 2024-01-17 |
Serdar Yüksel |
Q-Learning and its Convergence Part I:
Discounted Cost with Finite and Continuous Space
Models |
| 2023-01-24 |
Serdar Yüksel | Q-Learning and its Convergence Part II: Average Cost and Non-Markovian Dynamics |
| 2024-01-31 |
Somnath Pradhan |
Discrete-time Approximation of Ergodic Optimal Control
of Controlled Diffusions |
| 2024-02-07 |
Sina Sanjari (RMC) |
Large
Stochastic Teams with Mean-Field Sharing Information
Structure |
| 2024-02-14 |
Zachary Selk |
Large
Deviations for High Gaussian Minima |
| 2024-02-28 |
Yunus Emre Demirci |
Average
Cost Optimality in Partially Observable Markov
Decision Processes: Implications for Robustness and
Optimal Policy Approximation |
| 2024-03-05 |
Omar Mrani-Zentar |
Finite Memory Approximations for
Decentralized Stochastic Control |
| 2024-03-12 |
Liam Cregg |
Almost Sure Filter Stability for
Aperiodic Positive Harris Recurrent Markov Chains with
Nondegenerate Observations |
| 2024-03-26 |
Yichen Zhou |
Robustness to Noise Approximation in
Markov Decision Processes |
| 2024-04-03 |
Connor Braun |
Toward Decentralized Stochastic Control Models of Brain Function: An Introduction to Neural Systems |
| 2024-04-22 |
Serdar Yüksel | Robustness to Approximations and Incorrect Models in Stochastic Control |
| 2024-04-25 |
Serdar Yüksel | Stochastic Control with Partial Information: Regularity, Approximations, and Learning |
| 2024-04-29 |
Zachary Selk |
An Introduction to Stein's Method |
| 2024-05-06 |
Osman Biçer | Quantized Q-Learning for Finite Model Approximations of Continuous MDPs: Error Bounds with Non-Uniform Quantization |
| 2024-05-09 |
Yunus Emre Demirci | Stability of Nonlinear Filtering |
| 2024-05-12 |
Yunus Emre Demirci |
Stability of Nonlinear Filtering |
| 2024-05-16 | Connor Braun | Mean Field Markov Decision Processes |
| 2024-05-23 |
Omar Mrani-Zentar | An Overview of Alternatives to the Standard Q-learning Algorithm |
| 2024-06-03 |
Yichen Zhou | Wasserstein-p Metrics on Probability Measures |
| 2024-06-03 |
Evelyn Hubbard |
Jointly Optimal Coding and Control
Policies for a Markovian System Controlled over a
Communication Channel |
Summer: Mondays at 11am, Thursdays at 11am (Room 319).
Winter : Wednesday 14:30-15:30 (Room 422); unless an irregular seminar.
Fall : Fridays 15:45-17:00 (Room 319); unless an irregular seminar.