Sumários

Not Taught.

27 março 2024, 14:30 Manuel Cabido Lopes

materia terminada


Not Taught.

27 março 2024, 12:00 Francisco Saraiva de Melo

Matéria terminada.


Not Taught.

27 março 2024, 10:00 Manuel Cabido Lopes

materia terminada


12. Exploration vs. exploitation

26 março 2024, 15:00 Francisco Saraiva de Melo

Exploration vs. exploitation (Chap. 9):

  • The prediction problem (9.1)
  • Prediction with complete information: weighted majority and exponentially weighted averager (9.2)
  • Adversarial bandits and EXP3 (9.4)
  • Stochastic multi-armed bandits and UCB (9.3)
  • Applications:

    • Monte Carlo tree search
    • TD-Gammon
    • Alpha-Go
Wrap-up.


Session L5

26 março 2024, 08:30 Miguel Faria

Reinforcement learning.