HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem
Abstract
In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward. In this respect, we develop a novel meta reinforcement learning framework called Hyper-Meta RL(HMRL), for sparse reward RL problems. It is consisted with three modules including the cross-environment meta state embedding module which constructs a common meta state space to adapt to different environments; the meta state based environment-specific meta reward shaping which effectively extends the original sparse reward trajectory by cross-environmental knowledge complementarity and as a consequence the meta policy achieves better generalization and efficiency with the shaped meta reward. Experiments with sparse-reward environments show the superiority of HMRL on both transferability and policy learning efficiency.
Keywords
Cite
@article{arxiv.2002.04238,
title = {HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem},
author = {Yun Hua and Xiangfeng Wang and Bo Jin and Wenhao Li and Junchi Yan and Xiaofeng He and Hongyuan Zha},
journal= {arXiv preprint arXiv:2002.04238},
year = {2021}
}
Comments
13 pages