Hierarchical Imitation and Reinforcement Learning

Autor:	Le, Hoang M., Jiang, Nan, Agarwal, Alekh, Dudík, Miroslav, Yue, Yisong, Daumé III, Hal
Rok vydání:	2018
Předmět:	Computer Science - Learning Computer Science - Artificial Intelligence Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We propose an algorithmic framework, called hierarchical guidance, that leverages the hierarchical structure of the underlying problem to integrate different modes of expert interaction. Our framework can incorporate different combinations of imitation learning (IL) and reinforcement learning (RL) at different levels, leading to dramatic reductions in both expert effort and cost of exploration. Using long-horizon benchmarks, including Montezuma's Revenge, we demonstrate that our approach can learn significantly faster than hierarchical RL, and be significantly more label-efficient than standard IL. We also theoretically analyze labeling cost for certain instantiations of our framework. Comment: Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1803.00590 Zobrazit plný text záznamu View this record from Arxiv