Access the full text.
Sign up today, get DeepDyve free for 14 days.
J. Heemskerk, N. Sharkey (1996)
Learning subsumptions for an autonomous robot
N. Ono, Kenji Fukumoto (1996)
A Modular Approach to Multi-Agent Reinforcement Learning
M. Dorigo (1996)
Introduction to the Special Issue on Learning Autonomous RobotsIEEE Transactions on Systems, Man, and Cybernetics, 26
B. Kröse (1995)
Learning from delayed rewardsRobotics Auton. Syst., 15
(1996)
Consideration on conceptual design
(1996)
Learning Subsump tions for an Autonomous Robot," IEE seminar on self-learning robot, Digest No: 96/026
(1996)
Consideration on Concep tual Design of Inter Robot Communications Network for Mobile Robot System," Distributed Autonomous Robotic Systems 2 (DARS 96)
Claude Touzet is a scientist at the Center for Engineering Science Advanced Research at Oak Ridge National Laboratory (Tennessee). He received his M
J. Santos, C. Touzet (1999)
Exploration tuned reinforcement functionNeurocomputing, 28
L. Kaelbling, M. Littman, A. Moore (1996)
Reinforcement Learning: A SurveyJ. Artif. Intell. Res., 4
C. Kube, Hong Zhang (1993)
Collective Robotics: From Social Insects to RobotsAdaptive Behavior, 2
(1997)
Modular Approach to Multi-agent Reinforcement Learning," Distributed Arti cial Intelligence Meets Machine Learning: Learn ing in Multi-Agents
M. Muizon, Paul Cox, J. Lequeux (1989)
A survey of
C. Touzet (1997)
Neural reinforcement learning for behaviour synthesisRobotics Auton. Syst., 22
S. Whitehead, Jonas Karlsson, J. Tenenberg (1993)
Learning Multiple Goal Behavior via Task Decomposition and Dynamic Policy Merging, 3
L. Parker (1995)
The effect of action recognition and robot awareness in cooperative robotic teamsProceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots, 1
(1994)
Proc. of ESANN 94
L. Parker (1997)
Cooperative motion control for multi-target observationProceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97, 3
Matt Kretchmar, C. Anderson (1997)
Comparison of CMACs and radial basis functions for local function approximators in reinforcement learningProceedings of International Conference on Neural Networks (ICNN'97), 2
S. Sehad, C. Touzet (1994)
Reinforcement learning and neural reinforcement learning
R. Brooks (1991)
Intelligence Without Reason
V. Braitenberg (1984)
Vehicles, Experiments in Synthetic Psychology
L.J. Lin (1992)
Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 8
M. Matarić (1997)
Learning social behaviorRobotics Auton. Syst., 20
Yu Cao, A. Fukunaga, A. Kahng (1995)
Cooperative Mobile Robotics: Antecedents and DirectionsAutonomous Robots, 4
(1997)
Teaching Strategy for Memory-Based Control," Lazy Learning, D
(1990)
Explanations on this standard asymptotic notation can be found in Introduction to Algorithms
T. Balch, R. Arkin (1995)
Communication in reactive multiagent robotic systemsAutonomous Robots, 1
1(cid:12) >! (cid:4)+(cid:24)2(cid:9)(cid:5)(cid:8)$ (cid:5) ($/! (cid:31)(cid:18)(cid:159)7 (cid:2) =R/1)(cid:6)’*(cid:12)(cid:6)(cid:12)(cid:19)(cid:18)(cid:22)(cid:21) 8 (cid:4)
D. Aha (1997)
Lazy Learning
(1998)
Bias incorporation in robot learning, submitted for publication
M. Matarić (1997)
Reinforcement Learning in the Multi-Robot DomainAutonomous Robots, 4
Most of the straight-forward learning approaches in cooperative robotics imply for each learning robot a state space growth exponential in the number of team members. To remedy the exponentially large state space, we propose to investigate a less demanding cooperation mechanism—i.e., various levels of awareness—instead of communication. We define awareness as the perception of other robots locations and actions. We recognize four different levels (or degrees) of awareness which imply different amounts of additional information and therefore have different impacts on the search space size (Θ(0), Θ(1), Θ(N), o(N),1 where N is the number of robots in the team). There are trivial arguments in favor of avoiding binding the increase of the search space size to the number of team members. We advocate that, by studying the maximum number of neighbor robots in the application context, it is possible to tune the parameters associated with a Θ(1) increase of the search space size and allow good learning performance. We use the cooperative multi-robot observation of multiple moving targets (CMOMMT) application to illustrate our method. We verify that awareness allows cooperation, that cooperation shows better performance than a purely collective behavior and that learned cooperation shows better results than learned collective behavior.
Autonomous Robots – Springer Journals
Published: Oct 15, 2004
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.