Eppe, ManfredManfredEppeNguyen, Phuong D. H.Phuong D. H.NguyenWermter, StefanStefanWermter2022-04-252022-04-252019-11-26Frontiers in Robotics and AI 6 : 123 (2019-11-26)http://hdl.handle.net/11420/12353Reinforcement 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 discrete high-level action- and state spaces, whereas reinforcement learning is usually driven by a continuous reward 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 sparse rewards 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.en2296-91442019causal puzzleshierarchical architectureneural networksplanningreinforcement learningroboticsJournal Article10.3389/frobt.2019.00123Journal Article