From Semantics to Execution: Integrating Action Planning With Reinforcement Learning for Robotic Causal Problem-Solving

• Published in: Frontiers in robotics and AI 2019-11, Vol.6, p.123-123
• Main Authors: Eppe, Manfred, Nguyen, Phuong D H, Wermter, Stefan
• Format: Article
• Language: English
• Subjects: causal puzzles; hierarchical architecture; neural networks; planning; reinforcement learning; robotics; Robotics and AI
• ISSN: 2296-9144; 2296-9144
• DOI: 10.3389/frobt.2019.00123

Reinforcement learning is generally accepted to be an appropriate and successful method to learn robot control. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration of both approaches is that action planning is based on , whereas reinforcement learning is usually driven by a function. Recent advances in model-free reinforcement learning, specifically, universal value function approximators and hindsight experience replay, have focused on goal-independent methods based on that are only given at the end of a rollout, and only if the goal has been fully achieved. In this article, we build on these novel methods to facilitate the integration of action planning with model-free reinforcement learning. Specifically, the paper demonstrates how the reward-sparsity can serve as a bridge between the high-level and low-level state- and action spaces. As a result, we demonstrate that the integrated method is able to solve robotic tasks that involve non-trivial causal dependencies under noisy conditions, exploiting both data and knowledge.