Auxiliary Tasks and Exploration Enable ObjectNav
arXiv:2104.04112
Abstract
ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and recurrent modules, e.g. a CNN+RNN, perform poorly due to overfitting and sample inefficiency. This has motivated current state-of-the-art methods to mix analytic and learned components and operate on explicit spatial maps of the environment. We instead re-enable a generic learned agent by adding auxiliary learning tasks and an exploration reward. Our agents achieve 24.5% success and 8.1% SPL, a 37% and 8% relative improvement over prior state-of-the-art, respectively, on the Habitat ObjectNav Challenge. From our analysis, we propose that agents will act to simplify their visual inputs so as to smooth their RNN dynamics, and that auxiliary tasks reduce overfitting by minimizing effective RNN dimensionality; i.e. a performant ObjectNav agent that must maintain coherent plans over long horizons does so by learning smooth, low-dimensional recurrent dynamics. Site: https://joel99.github.io/objectnav/
References in corpus (10)
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- On Evaluation of Embodied Navigation Agents
- Learning to Navigate in Complex Environments
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
- Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
- Neural Predictive Belief Representations
- How recurrent networks implement contextual processing in sentiment analysis
- Learning Generalizable Visual Representations via Interactive Gameplay
- The geometry of integration in text classification RNNs