Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

From Tin Toy to Android

This presentation is intended to show the use of Adobe Presenter to create a narrated presentation, and can be compared with the version recorded using Camtasia Studio.

From Tin Toy to Android

This presentation is intended to show the use of Camtasia Studio to create a narrated presentation, and can be compared with the version recorded using Adobe Presenter.

Peer Feedback for Group Projects - Kenji Takeda

This is one of a series of short case studies describing how academic tutors at the University of Southampton have made use of learning technologies to support their students.

INFO2009 Reviews Partners, Commentary and Peer Review

guidance notes on review and evaluation processes. Part of the total handin required See also http://www.edshare.soton.ac.uk/9937/ for use in context and http://www.edshare.soton.ac.uk/9911/ for the guidance on the critical friend review process

PEER-REVIEWING, FEEDBACK & ASSESSMENT IN ENGINEERING TEACHING

Presentation

Sustaining Success Week 5 Task: Peer review guidance

Description of how to conduct a peer review, and guidance on how to submit it as a task. Download and edit this document if you decide to hand in information relating to your peer review exercise.

WEBS6203 Peer reviewing your reports

These notes contain a workflow, guidance notes, and supporting forms

FY2014-15 Peer Review

READ the guidance notes, then attempt the tasks CONTENTS: Peer review guidance

Scientific Journals, Peer Review and How to Write a Great Research Paper

Recording of the Elsevier Author Seminar by Dr Anthony Newman and Michaela Kurschildgen.

RTS-3 Task: Peer review guidance

Description of how to conduct a peer review