Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games.

Siqi Liu Marc Lanctot Luke Marris Nicolas Heess

Published in: ICML (2022)

Keyphrases

learning process
learning algorithm
learning systems
neural network
latent variable models
machine learning
reinforcement learning
online learning
learning tasks
decision trees
prior knowledge
linear programming
learning problems
feed forward
learning rules