PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning

State-of-the-art approaches to ObjectGoal navigation Prior work has made good progress on this task by rely on reinforcement learning and typically require significant formulating it as a reinforcement learning (RL) problem computational resources and time for learning. We and developing useful representations [20, 60], auxiliary propose Potential functions for ObjectGoal Navigation with tasks [61], data augmentation techniques [37], and improved Interaction-free learning (PONI), a modular approach that reward functions [37]. Despite this progress, end-toend disentangles the skills of'where to look?' for an object and RL incurs high computational cost, has poor sample efficiency, 'how to navigate to (x, y)?'. Our key insight is that'where and tends to generalize poorly to new scenes [7,12, to look?' can be treated purely as a perception problem, 37] since skills like moving without collisions, exploration, and learned without environment interactions. To address and stopping near the object are all learned from scratch this, we propose a network that predicts two complementary purely using RL. Modular navigation methods aim to address potential functions conditioned on a semantic map and uses these issues by disentangling'where to look for an object?' them to decide where to look for an unseen object. We train and'how to navigate to (x, y)?' [12,36]. These methods the potential function network using supervised learning on have emerged as strong competitors to end-to-end RL a passive dataset of top-down semantic maps, and integrate with good sample efficiency, better generalization to new it into a modular framework to perform ObjectGoal navigation.