NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations
arXiv:1906.07207
Abstract
We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian model, called NeoNav, which generates the next expected observations (NEO) conditioned on the current observations of the agent and the target view. Our generative model is learned through optimizing a variational objective encompassing two key designs. First, the latent distribution is conditioned on current observations and the target view, leading to a model-based, target-driven navigation. Second, the latent space is modeled with a Mixture of Gaussians conditioned on the current observation and the next best action. Our use of mixture-of-posteriors prior effectively alleviates the issue of over-regularized latent space, thus significantly boosting the model generalization for new targets and in novel scenes. Moreover, the NEO generation models the forward dynamics of agent-environment interaction, which improves the quality of approximate inference and hence benefits data efficiency. We have conducted extensive evaluations on both real-world and synthetic benchmarks, and show that our model consistently outperforms the state-of-the-art models in terms of success rate, data efficiency, and generalization.
arXiv commentadded experiments, accepted by AAAI, Corresponding author: Kai Xu ([email protected])
References in corpus (16)
- Continuous control with deep reinforcement learning
- Playing Atari with Deep Reinforcement Learning
- Trust Region Policy Optimization
- On Evaluation of Embodied Navigation Agents
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Imagination-Augmented Agents for Deep Reinforcement Learning
- The Predictron: End-To-End Learning and Planning
- Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
- Learning model-based planning from scratch
- Learning and Querying Fast Generative Models for Reinforcement Learning
- VAE with a VampPrior
- Semi-parametric Topological Memory for Navigation
- Visual Semantic Navigation using Scene Priors
- A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
- Gated Path Planning Networks