David Silver
Professor · University College London · ACM Prize Laureate
VP of Reinforcement Learning at Google DeepMind, Professor at UCL, and ACM Prize Laureate who led AlphaGo, AlphaZero, and AlphaStar.
- lectures
- 10
- series
- 1
- hours
- 16
Start here
Series and courses
Introduction to Reinforcement Learning
In these lectures
- A state possesses the Markov property if the future is independent of the past given the present.Markov Processes, Reward Processes & Bellman Equations
- Exploration allows an agent to gather information for better long-term decisions at the cost of short-term reward.Exploration and Exploitation
- Two-player zero-sum games possess a minimax value function and a minimax policy that corresponds to a Nash equilibrium.Classic Games
Draws on
People cited in the lectures, at the moment of the citation.
- Jerry TesauroResearcher at IBM who created TD-Gammon
- Michael LittmanPhD thesis on reinforcement learning algorithms converging on Nash equilibrium
- Claude ShannonFather of information theory, introduced minimax search and the first chess-playing program run on paper.
- Garry KasparovHuman world chess champion defeated by Deep Blue in 1997.
- Marion TinsleyDescribed as the greatest checkers player in history who only lost seven games in his career.
- Jonathan SchaefferMaker of Chinook who solved checkers in 2007.
Same subject, AI & Machine Learning
Connections
16Their places, courses, books and lectures.


