Model Primitive Hierarchical Lifelong Reinforcement Learning

4 Mar 2019  ·  Bohan Wu, Jayesh K. Gupta, Mykel J. Kochenderfer ·

Learning interpretable and transferable subpolicies and performing task decomposition from a single, complex task is difficult. Some traditional hierarchical reinforcement learning techniques enforce this decomposition in a top-down manner, while meta-learning techniques require a task distribution at hand to learn such decompositions. This paper presents a framework for using diverse suboptimal world models to decompose complex task solutions into simpler modular subpolicies. This framework performs automatic decomposition of a single source task in a bottom up manner, concurrently learning the required modular subpolicies as well as a controller to coordinate them. We perform a series of experiments on high dimensional continuous action control tasks to demonstrate the effectiveness of this approach at both complex single task learning and lifelong learning. Finally, we perform ablation studies to understand the importance and robustness of different elements in the framework and limitations to this approach.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here