Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Learning Functionally Decomposed Hierarchies for Continuous Control Tasks With Path Planning
Ist Teil von
IEEE robotics and automation letters, 2021-04, Vol.6 (2), p.3623-3630
Ort / Verlag
Piscataway: IEEE
Erscheinungsjahr
2021
Quelle
IEEE Xplore
Beschreibungen/Notizen
We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which allows the integration of task-relevant knowledge per layer. We propose an RL-based planner to efficiently leverage the information in the planning layer of the hierarchy, while the control layer learns a goal-conditioned control policy. The hierarchy is trained jointly but allows for the modular transfer of policy layers across hierarchies of different agents. We experimentally show that our method generalizes across unseen test environments and can scale to 3x horizon length compared to both learning and non-learning based methods. We evaluate on complex continuous control tasks with sparse rewards, including navigation and robot manipulation.