Preface to the special issue: adaptive learning agents

2016 ◽  
Vol 31 (1) ◽  
pp. 1-2
Author(s):  
Peter Vrancx ◽  
Enda Howley ◽  
Matt Knudson
Keyword(s):  
Adaptive Learning ◽  
Special Issue ◽  
Learning Agents

scholarly journals AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS

2011 ◽  
Vol 14 (02) ◽  
pp. 251-278 ◽  
Author(s):  
SAM DEVLIN ◽  
DANIEL KUDENKO ◽  
MAREK GRZEŚ
Keyword(s):  
Domain Knowledge ◽  
Group Performance ◽  
Stochastic Game ◽  
Multi Agent Systems ◽  
Learning Agents ◽  
Specific Behaviour ◽  
Reward Shaping ◽  
Multi Agent ◽  
The Impact ◽  
Final Group

This paper investigates the impact of reward shaping in multi-agent reinforcement learning as a way to incorporate domain knowledge about good strategies. In theory, potential-based reward shaping does not alter the Nash Equilibria of a stochastic game, only the exploration of the shaped agent. We demonstrate empirically the performance of reward shaping in two problem domains within the context of RoboCup KeepAway by designing three reward shaping schemes, encouraging specific behaviour such as keeping a minimum distance from other players on the same team and taking on specific roles. The results illustrate that reward shaping with multiple, simultaneous learning agents can reduce the time needed to learn a suitable policy and can alter the final group performance.

scholarly journals Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer

2020 ◽  
Author(s):  
Chao Shang ◽  
Sarthak Dash ◽  
Md. Faisal Mahbub Chowdhury ◽  
Nandana Mihindukulasooriya ◽  
Alfio Gliozzo
Keyword(s):  
Knowledge Transfer ◽  
Domain Knowledge ◽  
Cross Domain

scholarly journals Automated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style

2018 ◽  
Vol 12 (5) ◽  
pp. 4 ◽  
Author(s):  
Ibrahim Alkore Alshalabi ◽  
Samir E Hamada ◽  
Khaled Elleithy ◽  
Ioana Badara ◽  
Saeid Moslehpour
Keyword(s):  
Learning Style ◽  
Directed Graph ◽  
Adaptive Learning ◽  
Domain Knowledge ◽  
Learning System ◽  
Learning Goals ◽  
Educational Systems ◽  
Weighted Directed Graph ◽  
Path Graph ◽  
Learning Path

<p class="Abstract"><span>A directed graph represents an accurate picture of course descriptions for online courses through computer-based implementation of various educational systems. E-learning and m-learning systems are modeled as a weighted, directed graph where each node represents a course unit. The Learning Path Graph (LPG) represents and describes the structure of domain knowledge, including the learning goals, and all other available learning paths. In this paper, we propose a system prototype that implements a propose adaptive learning path algorithms that uses the student’s information from their profile and their learning style in order to improve the students’ learning performances through an m-learning system that provides a suitable course content sequence in a personalized manner.</span></p>

Preface to the special issue: Adaptive Learning Agents, Part 1

2014 ◽  
Vol 26 (1) ◽  
pp. 5-6
Author(s):  
Sam Devlin ◽  
Daniel Hennes ◽  
Enda Howley
Keyword(s):  
Adaptive Learning ◽  
Special Issue ◽  
Learning Agents
Sign in / Sign up

Export Citation Format

Share Document