Apprenticeship learning for helicopter control
نویسندگان
چکیده
منابع مشابه
Autonomous Helicopter Aerobatics through Apprenticeship Learning
Autonomous helicopter flight is widely regarded to be a highly challenging control problem. Despite this fact, human experts can reliably fly helicopters through a wide range of maneuvers, including aerobatic maneuvers at the edge of the helicopter’s capabilities. We present apprenticeship learning algorithms, which leverage expert demonstrations to efficiently learn good controllers for tasks ...
متن کاملBootstrapping Apprenticeship Learning
•We consider the problem of imitation learning where the examples, given by an expert, cover only a small part of a large state space. • Inverse Reinforcement Learning (IRL) provides an efficient tool for generalizing the partial demonstration, based on the assumption that the expert is maximizing an unknown utility function. • IRL consists in learning a reward function that explains the expert...
متن کاملStructured Apprenticeship Learning
We propose a graph-based algorithm for apprenticeship learning when the reward features are noisy. Previous apprenticeship learning techniques learn a reward function by using only local state features. This can be a limitation in practice, as often some features are misspecified or subject to measurement noise. Our graphical framework, inspired from the work on Markov Random Fields, allows to ...
متن کاملLearning Helicopter Control through \teaching by Showing"
A model-free "teaching by showing" methodology is developed to train a fuzzy-neural controller for an autonomous robot helicopter. The controller is generated and tuned using training data gathered while a teacher operates the helicopter. A hierarchical behavior-based control architecture is used, with each behavior implemented as a hybrid fuzzy logic controller (FLC) and general regression neu...
متن کاملSemi-Supervised Apprenticeship Learning
In apprenticeship learning we aim to learn a good policy by observing the behavior of an expert or a set of experts. In particular, we consider the case where the expert acts so as to maximize an unknown reward function defined as a linear combination of a set of state features. In this paper, we consider the setting where we observe many sample trajectories (i.e., sequences of states) but only...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Communications of the ACM
سال: 2009
ISSN: 0001-0782,1557-7317
DOI: 10.1145/1538788.1538812