期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 31, 期 2, 页码 369-386出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2015.2405593
关键词
Demonstration; inverse reinforcement learning (IRL); reward learning
类别
资金
- Office of Naval Research Science of Autonomy program [N000140910625]
Learning from demonstration provides an attractive solution to the problem of teaching autonomous systems how to perform complex tasks. Reward learning from demonstration is a promising method of inferring a rich and transferable representation of the demonstrator's intents, but current algorithms suffer from intractability and inefficiency in large domains due to the assumption that the demonstrator is maximizing a single reward function throughout the whole task. This paper takes a different perspective by assuming that the reward function behind an unsegmented demonstration is actually composed of several distinct subtasks chained together. Leveraging this assumption, a Bayesian nonparametric reward-learning framework is presented that infers multiple subgoals and reward functions within a single unsegmented demonstration. The new framework is developed for discrete state spaces and also general continuous demonstration domains using Gaussian process reward representations. The algorithm is shown to have both performance and computational advantages over existing inverse reinforcement learning methods. Experimental results are given in both cases, demonstrating the ability to learn challenging maneuvers from demonstration on a quadrotor and a remote-controlled car.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据