Statistical Learning
2 Projectiononthe(n,k)-simplex Weconsiderthefollowingprojectionproblem: pฮฑ(z)=argmin
Usually, this is done by projecting the score vector onto a probability simplex, and such projections are often characterized as Lipschitz continuous approximations of the argmax function, whose Lipschitz constant is controlled by a parameter that is similar to a softmax temperature.
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Beyond existing meta-RL analyses, we provide upper bounds of the expected optimality gap over the task distribution.