Figure 3: Exampleviewsofscenesfrom CLEVR-3D (left) and MSN-Easy (right). Figure 6: Novelview (left) withaslotremoved (center) oraslotaddedfromanotherscene (right).

In thispaper,weinvestigatewhether onesuchobjective,theWasserstein-1 distance between a policy's state visitation distribution and a target distribution, can be utilized effectivelyforreinforcement learning (RL)tasks.

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.