Through reinforcement learning (RL), we have made massive strides towards solving tasks that haveasingle goal. However,inthe multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affectsampleefficiency. Whenbiologicalagentslearn,thereisoftenanorganized and meaningful order to which learning happens. Inspired by this, we propose setting up an automatic curriculum for goals that the agent needs to solve.

Visual localization is a fundamental task in computer vision and robotics.

We study the Bayesian regret of the renowned Thompson Sampling algorithm incontextual bandits with binary losses and adversarially-selected contexts.

Notice implies Lorenz-dominance.Lor, states rankingisfair

However, directly applying existing subgame solving techniques may be difficult, due to the intricate nature and substantial size of many real-world games.

InComputerVision,however,almost all performant networks are "dense", that is, every input is processed by every parameter. We present a Vision MoE (V-MoE), a sparse version of the Vision Transformer, that is scalable and competitive with the largest dense networks.