Safe-To-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization

Policy search reinforcement learning allows <PRE_TAG>robot</POST_TAG>s to acquire skills by themselves. However, the learning procedure is inherently unsafe as the <PRE_TAG>robot</POST_TAG> has no a-priori way to predict the consequences of the exploratory actions it takes. Therefore, exploration can lead to collisions with the potential to harm the <PRE_TAG>robot</POST_TAG> and/or the environment. In this work we address the safety aspect by constraining the exploration to happen in safe-to-explore state spaces. These are formed by decomposing target <PRE_TAG>skills</POST_TAG> (e.g., grasping) into higher ranked sub-tasks (e.g., collision avoidance, joint limit avoidance) and lower ranked movement tasks (e.g., reaching). Sub-tasks are defined as concurrent controllers (policies) in different operational spaces together with associated Jacobians representing their joint-space mapping. Safety is ensured by only learning policies corresponding to lower ranked sub-tasks in the redundant null space of higher ranked ones. As a side benefit, learning in sub-manifolds of the state-space also facilitates sample efficiency. Reaching skills performed in simulation and grasping skills performed on a real <PRE_TAG><PRE_TAG>robot</POST_TAG></POST_TAG> validate the usefulness of the proposed approach.