Auxiliary Tasks Speed Up Learning PointGoal Navigation
arXiv:2007.04561
Abstract
PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. showed that this task is solvable but their method is computationally prohibitive, requiring 2.5 billion frames and 180 GPU-days. In this work, we develop a method to significantly increase sample and time efficiency in learning PointNav using self-supervised auxiliary tasks (e.g. predicting the action taken between two egocentric observations, predicting the distance between two observations from a trajectory,etc.).We find that naively combining multiple auxiliary tasks improves sample efficiency,but only provides marginal gains beyond a point. To overcome this, we use attention to combine representations learnt from individual auxiliary tasks. Our best agent is 5.5x faster to reach the performance of the previous state-of-the-art, DD-PPO, at 40M frames, and improves on DD-PPO's performance at 40M frames by 0.16 SPL. Our code is publicly available at https://github.com/joel99/habitat-pointnav-aux.
arXiv comment8 pages. Accepted to CoRL 2020
References in corpus (17)
- A Simple Framework for Contrastive Learning of Visual Representations
- Representation Learning with Contrastive Predictive Coding
- Improved Baselines with Momentum Contrastive Learning
- Learning deep representations by mutual information estimation and maximization
- Momentum Contrast for Unsupervised Visual Representation Learning
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Contrastive Multiview Coding
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- On Evaluation of Embodied Navigation Agents
- Learning to Navigate in Complex Environments
- Unsupervised Visual Representation Learning by Context Prediction
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
- Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
- Neural Predictive Belief Representations
- DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
- Situational Fusion of Visual Representation for Visual Navigation
- Embodied Question Answering in Photorealistic Environments with Point Cloud Perception