One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Abstract

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stochastic environmental augmentation, to demonstrate successful zero-shot transfer under real-world environmental variations without fine-tuning.

NIPS Workshop on Acting and Interacting in the Real World: Challenges in Robot Learning

References in corpus (6)

• Benchmarking Deep Reinforcement Learning for Continuous Control
• Deep Exploration via Bootstrapped DQN
• A Distributional Perspective on Reinforcement Learning
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
• Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

Cited by in corpus (13)

• Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
• Deep Reinforcement Learning (DRL): Another Perspective for Unsupervised Wireless Localization
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
• Learning to Navigate in Cities Without a Map
• Leveraging Siamese Networks for One-Shot Intrusion Detection Model
• Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal
• Deep Learning for Embodied Vision Navigation: A Survey
• Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
• Cross-View Policy Learning for Street Navigation
• Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning
• Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
• Evaluating task-agnostic exploration for fixed-batch learning of arbitrary future tasks