One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay
This addresses the challenge of data efficiency for robotics applications, though it is incremental as it focuses on a specific navigation setup.
The paper tackles the problem of costly real-world interaction in robot navigation by introducing a method that learns from a single traversal of the environment, achieving successful zero-shot transfer under real-world variations without fine-tuning.
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.