Isaac Newton Institute Seminars

12
Nov

Scaling Multi-Agent Reinforcement Learning to the Mean-Field Regime

Speaker:

Batu Yardim (ETH Zürich)

Time:

Wednesday, November 12, 2025 - 14:40 to 15:20

Venue:

Seminar Room 1, Newton Institute

12
Nov

title and abstract tba

Speaker:

Jing Tao (University of Oklahoma)

Time:

Wednesday, November 12, 2025 - 15:00 to 16:00

Venue:

Seminar Room 2, Newton Institute

12
Nov

Open problems in Q-learning

Speaker:

Sean Meyn (University of Florida)

Time:

Wednesday, November 12, 2025 - 15:50 to 16:30

Venue:

Seminar Room 1, Newton Institute

12
Nov

Break

Speaker:

Time:

Wednesday, November 12, 2025 - 16:00 to 16:30

Venue:

Foyer

12
Nov

Title TBC

Speaker:

Georgios Batzolis (University of Cambridge)

Time:

Wednesday, November 12, 2025 - 16:30 to 17:10

Venue:

Seminar Room 1, Newton Institute

12
Nov

Formal Dinner at Robinson College

Speaker:

Time:

Wednesday, November 12, 2025 - 19:00 to 22:00

Venue:

External

13
Nov

Quantized Q-Learning for Stochastic Control with Borel Spaces and General Information Structures

Speaker:

Serdar Yuksel (Queen's University, Canada)

Time:

Thursday, November 13, 2025 - 09:00 to 09:40

Venue:

Seminar Room 1, Newton Institute

13
Nov

Quantifying Sensitivity to Model Uncertainty

Speaker:

Jan Obłój (University of Oxford)

Time:

Thursday, November 13, 2025 - 09:40 to 10:20

Venue:

Seminar Room 1, Newton Institute

13
Nov

Break

Speaker:

Time:

Thursday, November 13, 2025 - 10:30 to 11:00

Venue:

Foyer

13
Nov

New Relative Value Iteration and Q-Learning Algorithms for Ergodic Risk Sensitive Control of Markov Chains

Speaker:

Guodong Pang (Rice University)

Time:

Thursday, November 13, 2025 - 10:50 to 11:30

Venue:

Seminar Room 1, Newton Institute

13
Nov

Contextual Bilevel Reinforcement Learning for Incentive Alignment

Speaker:

Yifan Hu (Rutgers, The State University of New Jersey)

Time:

Thursday, November 13, 2025 - 11:30 to 12:10

Venue:

Seminar Room 1, Newton Institute

13
Nov

Lunch

Speaker:

Time:

Thursday, November 13, 2025 - 12:30 to 14:30

Venue:

Churchill College

13
Nov

Title TBC

Speaker:

David Silver (Google DeepMind Technologies Limited)

Time:

Thursday, November 13, 2025 - 14:00 to 14:40

Venue:

Seminar Room 1, Newton Institute

13
Nov

Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain

Speaker:

Shengbo Wang (University of Southern California)

Time:

Thursday, November 13, 2025 - 14:40 to 15:20

Venue:

Seminar Room 1, Newton Institute

13
Nov

Title TBC

Speaker:

Michal Valko (INRIA Lille - Nord Europe Research Centre)

Time:

Thursday, November 13, 2025 - 15:50 to 16:30

Venue:

Seminar Room 1, Newton Institute

13
Nov

Break

Speaker:

Time:

Thursday, November 13, 2025 - 16:00 to 16:30

Venue:

Foyer

13
Nov

Convergence of the actor-critic gradient flow for entropy regularised MDPs in general action spaces

Speaker:

David Siska (University of Edinburgh)

Time:

Thursday, November 13, 2025 - 16:30 to 17:10

Venue:

Seminar Room 1, Newton Institute

14
Nov

Free Discussion

Speaker:

Time:

Friday, November 14, 2025 - 09:00 to 10:20

Venue:

Seminar Room 1, Newton Institute

14
Nov

Break

Speaker:

Time:

Friday, November 14, 2025 - 10:30 to 11:00

Venue:

Foyer

14
Nov

Free Discussion

Speaker:

Time:

Friday, November 14, 2025 - 10:50 to 12:10

Venue:

Seminar Room 1, Newton Institute

12
Nov

Scaling Multi-Agent Reinforcement Learning to the Mean-Field Regime

12
Nov

title and abstract tba

12
Nov

Open problems in Q-learning

12
Nov

Break

12
Nov

Title TBC

12
Nov

Formal Dinner at Robinson College

13
Nov

Quantized Q-Learning for Stochastic Control with Borel Spaces and General Information Structures

13
Nov

Quantifying Sensitivity to Model Uncertainty

13
Nov

Break

13
Nov

New Relative Value Iteration and Q-Learning Algorithms for Ergodic Risk Sensitive Control of Markov Chains

13
Nov

Contextual Bilevel Reinforcement Learning for Incentive Alignment

13
Nov

Lunch

13
Nov

Title TBC

13
Nov

Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain

13
Nov

Title TBC

13
Nov

Break

13
Nov

Convergence of the actor-critic gradient flow for entropy regularised MDPs in general action spaces

14
Nov

Free Discussion

14
Nov

Break

14
Nov

Free Discussion

Forthcoming Seminars

News, Announcements and Events

Study at Cambridge

About the University

Research at Cambridge

Isaac Newton Institute Seminars

12Nov Scaling Multi-Agent Reinforcement Learning to the Mean-Field Regime

12Nov title and abstract tba

12Nov Open problems in Q-learning

12Nov Break

12Nov Title TBC

12Nov Formal Dinner at Robinson College

13Nov Quantized Q-Learning for Stochastic Control with Borel Spaces and General Information Structures

13Nov Quantifying Sensitivity to Model Uncertainty

13Nov Break

13Nov New Relative Value Iteration and Q-Learning Algorithms for Ergodic Risk Sensitive Control of Markov Chains

13Nov Contextual Bilevel Reinforcement Learning for Incentive Alignment

13Nov Lunch

13Nov Title TBC

13Nov Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain

13Nov Title TBC

13Nov Break

13Nov Convergence of the actor-critic gradient flow for entropy regularised MDPs in general action spaces

14Nov Free Discussion

14Nov Break

14Nov Free Discussion

Forthcoming Seminars

News, Announcements and Events

Study at Cambridge

About the University

Research at Cambridge

12
Nov

Scaling Multi-Agent Reinforcement Learning to the Mean-Field Regime

12
Nov

title and abstract tba

12
Nov

Open problems in Q-learning

12
Nov

Break

12
Nov

Title TBC

12
Nov

Formal Dinner at Robinson College

13
Nov

Quantized Q-Learning for Stochastic Control with Borel Spaces and General Information Structures

13
Nov

Quantifying Sensitivity to Model Uncertainty

13
Nov

Break

13
Nov

New Relative Value Iteration and Q-Learning Algorithms for Ergodic Risk Sensitive Control of Markov Chains

13
Nov

Contextual Bilevel Reinforcement Learning for Incentive Alignment

13
Nov

Lunch

13
Nov

Title TBC

13
Nov

Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain

13
Nov

Title TBC

13
Nov

Break

13
Nov

Convergence of the actor-critic gradient flow for entropy regularised MDPs in general action spaces

14
Nov

Free Discussion

14
Nov

Break

14
Nov

Free Discussion