Tata Institute of Fundamental Research
Teaching Your Computer to Play Chess (Part 1): Markov Games and TD Learning
STCS Student Seminar
Speaker:
Aakash Ghosh (TIFR)
Organiser:
Nishant Das
Date:
Friday, 24 Apr 2026, 16:00 to 17:00
Venue:
A201
(Scan to add to calendar)
Abstract:
How do we mathematically formulate the problem of learning to play a game as complex as chess? In the first part of this two-part series, we will approach chess through the lens of Reinforcement Learning and Stochastic Approximation. We begin by formalizing the game as a two-player zero-sum Markov Decision Process, discussing the Bellman Optimality Equation and minimax equilibria.
| Speaker: | Aakash Ghosh (TIFR) |
| Organiser: | Nishant Das |
| Date: | Friday, 24 Apr 2026, 16:00 to 17:00 |
| Venue: | A201 |
(Scan to add to calendar)
Abstract:
How do we mathematically formulate the problem of learning to play a game as complex as chess? In the first part of this two-part series, we will approach chess through the lens of Reinforcement Learning and Stochastic Approximation. We begin by formalizing the game as a two-player zero-sum Markov Decision Process, discussing the Bellman Optimality Equation and minimax equilibria.