Minimax Decision Rule

A Minimax Decision Rule is a decision rule that minimize a maximum loss.

• AKA: Minimax.
  • …
• Counter-Example(s):
  • a Bayes Rule (that minimized an average loss).
• See: Decision Theory, Loss Function, Zero-Sum, Minimax Estimator, Minimax Value.

---

---

References

2015

• (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Minimax Retrieved:2015-9-15.
  • Minimax (sometimes MinMax or MM ) is a decision rule used in decision theory, game theory, statistics and philosophy for minimizing the possible loss for a worst case (maximum loss) scenario. Originally formulated for two-player zero-sum game theory, covering both the cases where players take alternate moves and those where they make simultaneous moves, it has also been extended to more complex games and to general decision making in the presence of uncertainty.

---