Markov Decision Process and Reinforcement Learning Workshop

Event Date
--
Winstanley Lecture Theatre, Trinity College

The Janeway Institute and the Department of Mathematics and the Department of Economics at the National University of Singapore co-sponsored a workshop on "Markov Decision Process and Reinforcement Learning", from 22nd-23rd September 2023.

Download the event programme here.  Or, see below:

 

Programme

Date: 22 September 2023 (Friday)
Venue: Winstanley Lecture Theatre, Trinity College, Cambridge

9:30 - 9:55 Registration

9:55 - 10:00 Opening Speech

Session 1

10:00 – 10:35 Agostino Capponi (Columbia University)
Title: Market Microstructure in the Big-data Era: Improving High-frequency Price Prediction via Machine Learning

10:35 - 11:10 Patrick Cheridito (ETH Zurich)
Title: Deep Trade Execution

11:10 - 11:30 Tea Break

11:30 - 12:05 Yijiong Zhang, (NUS [Chongqing] Research Institute)
Title: Optimal Market Making in a Multi-agent Market under Model Uncertainty: A Reinforcement Learning Approach

12:05 - 12:40 Wolfgang Karl Haerdle (Humboldt University Berlin)
Title: Regime-switching Reinforcement Learning

12:40 - 14:30 Lunch

Session 2 

14:30 - 15:05 Peter Bossaerts (University of Cambridge)
Title: Statistical Efficiency in Human and Machine Reinforcement Learning

15:05 - 15:40 Sorawoot Srisuma (National University of Singapore and University of Surrey)
Title: Least Squares Estimation of Dynamic Games with Unobserved Heterogeneity

15:40 - 16:15 Karun Adusumili (UPenn)
Title: Temporal Difference Estimation of Dynamic Discrete Choice Models

16:15 - 16:30 Tea Break

16:30 - 17:05 Tomaso Aste (UCL)
Title : Network Modeling for Complex Systems

17:05 - 17:40 Alessio Sancetta (Royal Holloway, University of London)
Title: Action-State Dependent Dynamic Model Selection

17:40 -18:15 Julian Sester (NUS)
Title: Markov Decision Processes under Model Uncertainty 2

19:00 Speakers’ and Organisers’ Dinner*

Date: 23 September 2023 (Saturday)

Venue: Winstanley Lecture Theatre, Trinity College, Cambridge

Session 1

10:00 - 10:35 Xiaohong Chen (Yale University)
Title: STEEL: Singularity-aware Reinforcement Learning

10:35 - 11:10 Chengchun Shi (LSE)
Title: Doubly Inhomogeneous Reinforcement Learning

11:10 - 11:30 Tea Break

11:30 - 12:05 Tetsuya Kaji (Chicago Booth)
Title: An Adversarial Approach to Structural Estimation

12:05 - 12:40 Ruohan Zhan (HKUST)
Title: Post-Episodic Reinforcement Learning Inference

12:40 - 14:30 Lunch Break

Session 2 

14:30 – 15:05 Masashi Sugiyama (RIKEN/The University of Tokyo)
Title: Learning under Continuous Distribution Shifts

15:05 - 15:40 Bo An (Nanyang Technological University)
Title: Reinforcement Learning for Handling Complex Multi-agent Interactions

15:40 - 16:00 Closing Remarks & Farewell

 

For enquiries, contact Marion Reusch