Exploring Deep and Recurrent Architectures for Optimal Control
نویسنده
چکیده
Sophisticated multilayer neural networks have achieved state of the art results on multiple supervised tasks. However, successful applications of such multilayer networks to control have so far been limited largely to the perception portion of the control pipeline. In this paper, we explore the application of deep and recurrent neural networks to a continuous, high-dimensional locomotion task, where the network is used to represent a control policy that maps the state of the system (represented by joint angles) directly to the torques at each joint. By using a recent reinforcement learning algorithm called guided policy search, we can successfully train neural network controllers with thousands of parameters, allowing us to compare a variety of architectures. We discuss the differences between the locomotion control task and previous supervised perception tasks, present experimental results comparing various architectures, and discuss future directions in the application of techniques from deep learning to the problem of optimal control.
منابع مشابه
Deep Q-Learning With Recurrent Neural Networks
Deep reinforcement learning models have proven to be successful at learning control policies image inputs. They have, however, struggled with learning policies that require longer term information. Recurrent neural network architectures have been used in tasks dealing with longer term dependencies between data points. We investigate these architectures to overcome the difficulties arising from ...
متن کاملReal-time optimal control via Deep Neural Networks: study on landing problems
Recent research on deep learning, a set of machine learning techniques able to learn deep architectures, has shown how robotic perception and action greatly benefits from these techniques. In terms of spacecraft navigation and control system, this suggests that deep architectures may be considered now to drive all or part of the onboard decision making system. In this paper this claim is invest...
متن کاملBidirectional truncated recurrent neural networks for efficient speech denoising
We propose a bidirectional truncated recurrent neural network architecture for speech denoising. Recent work showed that deep recurrent neural networks perform well at speech denoising tasks and outperform feed forward architectures [1]. However, recurrent neural networks are difficult to train and their simulation does not allow for much parallelization. Given the increasing availability of pa...
متن کاملThe importance of the optimal volume in the treatment of locally recurrent nasopharyngeal carcinoma; brachytherapy or stereotactic radiotherapy?
Introduction: Nasopharyngeal carcinoma (NPC) is commonly known as a radiosensitive tumor with the initial good response to radiation. Despite the improved outcome in loco regional control by the introduction of combining treatment, modern radiotherapy techniques and enhanced imaging studies, local recurrent after primary treatment with rate ranges from 15-58% in 5 years, stil...
متن کاملIterative Deep Aggregation Hierarchical Deep Aggregation
Architectural efforts are exploring many dimensions for network backbones, designing deeper or wider architectures, but how to best aggregate layers and blocks across a network deserves further attention. We augment standard architectures with deeper aggregation to better fuse information across layers. Our deep layer aggregation structures iteratively and hierarchically merge the feature hiera...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1311.1761 شماره
صفحات -
تاریخ انتشار 2013