search

Jamesflynn1 / CS344-Opponent-Exploitation-Poker

A third year uni project aiming to implement and evaluate the EFR algorithm with different deviation types and explore a potential tradeoff between exploitability and expected value of a strategy in practice.
0 stars 0 forks source link

Training time requirements #18

Closed Jamesflynn1 closed 1 year ago

Jamesflynn1 commented 1 year ago

# Training time will again depend on the details of the algorithm and will be decided after such time. #

Originally posted by @Jamesflynn1 in https://github.com/Jamesflynn1/CS344-Opponent-Modelling-Poker/issues/16#issuecomment-1292337429

Jamesflynn1 commented 1 year ago

Two sets of experiments, each with roughly 25 sub experiments, might need to narrow this down is computation is too extensive. Alternatively, more abstraction could be applied.

Jamesflynn1 commented 1 year ago

Looks relatively good based on Morrill's own experiments and easy use of abstraction