S. Mahadevan, J. Connell  Home/Search
Context Related
| msu.edu/~mahadeva/...obelixpaper.ps.Z umn.edu/users/gini...ijobelixpaper.ps msu.edu/~mahadeva/...obelixpaper.ps.Z Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: cs.ubc.ca/spider/poole/ml/1998... (more) From: umn.edu/~gini/8551/reading (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper describes a general approach for automatically programming a behavior-based robot. New behaviors are learned by trial and error using a performance feedback function as reinforcement. Two algorithms for behavior learning are described that combine Q learning, a well known scheme for propagating reinforcement values temporally across actions, with statistical clustering and Hamming distance, two ways of propagating reinforcement values spatially across states. A real behavior-based... (Update)
Similar documents based on text: More All
0.6: Bibliography - Sheppard (Correct)
0.5: January, 1996. - Watkins Learning From (Correct)
0.5: Model-Based Learning of Interaction Strategies in Multi-Agent.. - Carmel (1997) (Correct)
Related documents from co-citation: More All
32: Learning to predict by the method of temporal differences - Sutton - 1988
31: Learning to coordinate behaviors - Maes, Brooks - 1990
31: Learning from Delayed Rewards (context) - CJCH - 1989
BibTeX entry: (Update)
Mahadevan, S. & Connell, J. (1991), Automatic Programming of Behavior-based Robots using Reinforcement Learning, in `Proceedings, AAAI-91', Pittsburgh, PA, pp. 8--14. http://citeseer.ist.psu.edu/mahadevan91automatic.html More
@inproceedings{ mahadevan91automatic,
author = "Sridhar Mahadevan and Jonathan Connell",
title = "Automatic Programming of Behavior-Based Robots Using Reinforcement Learning",
booktitle = "National Conference on Artificial Intelligence",
pages = "768-773",
year = "1991",
url = "citeseer.ist.psu.edu/mahadevan91automatic.html" }
Citations (may not include all citations):1364 A robust layered control system for a mobile robot (context) - Brooks - 1986
233 Neuronlike adaptive elements that can solve difficult learni.. (context) - Barto, Sutton et al. - 1983
33 and Robotics (context) - Albus, Behaviors - 1981
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.ubc.ca/spider/poole/ml/1998/):
Reward Functions for Accelerated Learning - Mataric (1994) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC