Model Primitive Hierarchical Lifelong Reinforcement Learning
By Bohan Wu, Jayesh K. Gupta, Mykel J. Kochenderfer. 2019
10 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Vincenzo Lomonaco
- Davide Maltoni
- Karan Desai
- Eugenio Culurciello
- Lorenzo Pellegrini
- Timothée Lesort
- German Ignacio Parisi
- Jiangpeng He
Citations in the corpus
- Continual Reinforcement Learning in 3D Non-stationary Environments (2019, background): “Recent works in this research area include meta-learning [12, 35, 1], hierarchical learning [50, 49] and continual learning approaches [21, 43, 37].”