Compositional Transfer in Hierarchical Reinforcement Learning

Robotics - Science and Systems(2020)

引用 31|浏览346
暂无评分
摘要
The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements. We introduce Regularized Hierarchical Policy Optimization (RHPO) to improve data-efficiency for domains with multiple dominant tasks and ultimately reduce required platform time. To this end, we employ compositional inductive biases on multiple levels and corresponding mechanisms for sharing off-policy transition data across low-level controllers and tasks as well as scheduling of tasks. The presented algorithm enables stable and fast learning for complex, real-world domains in the parallel multitask and sequential transfer case. We show that the investigated types of hierarchy enable positive transfer while partially mitigating negative interference and evaluate the benefits of additional incentives for efficient, compositional task solutions in single task domains. Finally, we demonstrate substantial data-efficiency and final performance gains over competitive baselines in a week-long, physical robot stacking experiment.
更多
查看译文
关键词
reinforcement,compositional,learning,transfer
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要