New answers tagged artificial-intelligence
1
Algorithm 1, which I refer to in the question, produces a strategy that minimizes cumulative counterfactual regret.
The motivation is to get a strategy which minimizes overall regret (as defined earlier in the paper). That's because such a strategy approximates a nash equilibrium strategy.
In other words, cumulative counterfactual regret was designed to be:
...
Top 50 recent answers are included
