AIExplainer

What is minimax loss?

A loss function used in machine learning to train models, especially in game-playing AI and reinforcement learning

Minimax loss is a way to measure how well a model is doing by considering the best and worst possible outcomes. It tries to minimize the maximum loss, which means it aims to reduce the worst-case scenario.

Imagine you're playing a game of chess. The minimax loss is like thinking about the best move you can make to win, while also considering the worst move your opponent could make to beat you. You're trying to minimize the loss of the game by thinking about the maximum possible loss.

AlphaGo, a computer program that plays Go, used minimax loss to train its model and defeat a human world champion. The model considered all possible moves and their outcomes, and adjusted its strategy to minimize the maximum loss.

Minimax loss is used in training models to make decisions in complex, uncertain environments, such as game-playing AI, robotics, and finance. It helps models to learn from their mistakes and improve their performance over time.

Some people think that minimax loss is only used in game-playing AI, but it's also used in other areas, such as finance and robotics, where models need to make decisions under uncertainty.

The concept of minimax loss originated in the 1920s in the field of game theory, and was later adopted in machine learning and artificial intelligence.

minimax algorithm saddlepoint loss game-theoretic loss

Three products for different needs — explore what’s relevant to you.