Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulation
This addresses the challenge of explainable decision-making in human-robot interactions, though it appears incremental as it builds on existing hierarchical reinforcement learning methods.
The paper tackles the problem of interpretability in robotic manipulation by proposing a hierarchical deep reinforcement learning system called Dot-to-Dot, which enables efficient learning of complex actions and states while providing an interpretable high-level representation for human operators, tested on MuJoCo-based models with successful results.
Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence. However, as robots and humans come closer in their interactions, the matter of interpretability, or explainability of robot decision-making processes for the human grows in importance. A successful interaction and collaboration will only take place through mutual understanding of underlying representations of the environment and the task at hand. This is currently a challenge in deep learning systems. We present a hierarchical deep reinforcement learning system, consisting of a low-level agent handling the large actions/states space of a robotic system efficiently, by following the directives of a high-level agent which is learning the high-level dynamics of the environment and task. This high-level agent forms a representation of the world and task at hand that is interpretable for a human operator. The method, which we call Dot-to-Dot, is tested on a MuJoCo-based model of the Fetch Robotics Manipulator, as well as a Shadow Hand, to test its performance. Results show efficient learning of complex actions/states spaces by the low-level agent, and an interpretable representation of the task and decision-making process learned by the high-level agent.