[Research] We improve reliable, long-horizon, goal-directed navigation in partially-mapped environments by using non- locally available information to predict the goodness of temporally-extended actions that enter unseen space.
[Research] We present a fast and reliable policy selection approach for navigation in partial maps that leverages information collected during deployment to introspect the behavior of alternative policies without deployment.
[Research] We generate explanations of a robot agent’s behavior as it navigates through a partially-revealed environment, expressed in terms of changes to its predictions about what lies in unseen space. Blog post accompanying our NeurIPS 2021 paper.
[Research] Using DeepMind’s AlphaZero AI to solve real problems will require a change in the way computers represent and think about the world. In this post, we discuss how abstract models of the world can be used for better AI decision making and discuss recent work of ours that proposes such a model for the task of navigation.