Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments
This addresses the problem of quick adaptation for robots in changing environments, though it is incremental as it builds on existing successor feature methods.
The paper tackles robot navigation in maze-like environments without requiring localization, mapping, or planning, proposing a successor feature-based deep reinforcement learning algorithm that transfers knowledge from mastered tasks to new instances, reducing learning time by up to 50% in experiments.
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.