Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

TL;DR

This paper introduces a successor feature-based deep reinforcement learning approach for robot navigation that enables quick adaptation to new environments without localization or mapping, demonstrated through simulated and real robot experiments.

Contribution

The paper presents a novel successor feature-based deep reinforcement learning algorithm that transfers knowledge across related navigation tasks, reducing learning time in changing environments.

Findings

Significantly reduces learning time after initial task completion.

Effective in both simulated and real robot navigation scenarios.

Outperforms classical planning-based methods in experiments.

Abstract

In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additionally, we require that our solution can quickly adapt to new situations (e.g., changing navigation goals and environments). To meet these criteria we frame this problem as a sequence of related reinforcement learning tasks. We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances. Our algorithm substantially decreases the required learning time after the first task instance has been solved, which makes it easily adaptable to changing environments. We validate our method in both simulated and real robot experiments with a Robotino and compare it to a set of baseline methods including classical planning-based navigation.