Jordan Pollack, Alan D. Blair, Mark Land  Home/Search
Context Related
| brandeis.edu/papers/alife5.ps.Z uq.edu.au/personal/blair/alife5.ps.Z uq.edu.au/personal/b...alife_hcgam.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: brandeis.edu/papers/long (more) From: uq.edu.au/personal/blair/pub Homepages: A.Blair |
Rate this article:      (best)Comment on this article |
Abstract: One of the persistent themes in Artificial Life research is the use of co-evolutionary arms races in the development of specific and complex behaviors. However, other than Sims's work on artificial robots, most of the work has attacked very simple games of prisoners dilemma or predator and prey. Following Tesauro's work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of the dice, application of... (Update)
Context of citations to this paper: More
.... by embedding the learner in a learning environment which responds to its own improvements in a never ending spiral (Pollack) [9]. Moriarty gives a survey into general learning with evolutionary algorithms [8] In 2000, Chellapilla and Fogel successfully developed...
.... Rather than enter a progressive arms race, competing populations may stabilise into a suboptimal equilibrium, or mediocre stable state [3, 7, 8, 6]. As individuals are only rewarded for out performing their contemporary oponents, it is possible for earlier adaptations to be...
Cited by: More
Temporal-Difference Learning in Self-Play Training - Clifford Kotnik Clkotnik (2003) (Correct)
Comparing a Coevolutionary Genetic Algorithm for.. - Lohn, Kraus, Haith (2002) (Correct)
Integrating Reinforcement Learning, Bidding and Genetic Algorithms - Qi, Sun (2003) (Correct)
Similar documents (at the sentence level):
40.9%: Why did TD-Gammon Work? - Pollack, Blair (1997) (Correct)
25.4%: Co-Evolution in the Successful Learning of Backgammon Strategy - Pollack, Blair (1998) (Correct)
Active bibliography (related documents): More All
0.3: What Makes a Good Co-Evolutionary Learning Environment? - Blair, Pollack (1997) (Correct)
0.2: Coevolutionary Search Among Adversaries - Rosin (1997) (Correct)
0.1: Co-evolutionary Learning: Machines and Humans Schooling Together - Sklar (1998) (Correct)
Similar documents based on text: More All
0.4: Dynamics of Co-evolutionary Learning - Juille, Pollack (1996) (Correct)
0.4: Co-evolution, Determinism and Robustness - Blair (Correct)
Related documents from co-citation: More All
10: Some studies in machine learning using the game of checkers (context) - Samuel - 1957
9: Genetic Programming: On the Programming of Computers by Means of Natural Selecti.. (context) - Koza - 1992
9: Temporal Difference Learning and TD-Gammon (context) - Gerald - 1995
BibTeX entry: (Update)
J. Pollack, A. Blair, and M. Land. Coevolution of a Backgammon Player. In Proceedings of the Fifth Artificial Life Conference, Nara, Japan, 1996. http://citeseer.ist.psu.edu/pollack96coevolution.html More
@inproceedings{ pollack97coevolution,
author = "Jordan B. Pollack and Alan D. Blair and Mark Land",
title = "Coevolution of a Backgammon Player",
booktitle = "Artificial {L}ife {V}: {P}roc.\ of the {F}ifth {I}nt.\ Workshop on the {S}ynthesis and {S}imulation of {L}iving {S}ystems",
publisher = "The MIT Press",
address = "Cambridge, MA",
editor = "Christopher G. Langton and Katsunori Shimohara",
pages = "92--98",
year = "1997",
url = "citeseer.ist.psu.edu/pollack96coevolution.html" }
Citations (may not include all citations):1931 Adaptation in Natural and Artificial Systems (context) - Holland - 1975
563 Learning to predict by the methods of temporal differences - Sutton - 1988
432 The evolution of cooperation (context) - Axelrod - 1984
233 Neuronlike adaptive elements that can solve difficult learni.. (context) - Barto, Sutton et al. - 1983
219 Practical issues in temporal difference learning - Tesauro - 1992
205 Co-evolving parasites improves simulated evolution as an opt.. (context) - Hillis - 1992
199 Markov games as a framework for multi-agent reinforcement le.. - Littman - 1994
149 An approach to the synthesis of life (context) - Ray - 1992
141 The origins of Order: Self-Organization and Selection in Evo.. (context) - Kauffman - 1993
110 Temporal difference learning and TD-Gammon (context) - Tesauro - 1995
86 Evolutionary phenomena in simple dynamics (context) - Lindgren - 1992
82 Competitive environments evolve better solutions for complex.. - Angeline, Pollack - 1994
43 Tracking the red queen: Measurements of adaptive progress in.. - Cliff, Miller - 1995
34 Temporal difference learning of position evaluation in the g.. - Schraudolph, Dayan et al. - 1994
24 Modular neural networks for learning context-dependent game .. - Boyan - 1992
19 Massively parallel genetic programming - Juille, Pollack - 1995
16 Toward an ideal trainer (context) - Epstein - 1994
16 Using evolutionary programming to create neural networks tha.. (context) - Fogel - 1993
12 and the game of tag (context) - Reynolds - 1994
9 An alternate interpretation of the iterated prisoner's dilem.. - Angeline - 1994
9 The Hedonistic Neuron (context) - Klopf - 1982
6 Trial and error (context) - Michie - 1961
3 IBM's family funpak for OS/2 Warp hits retail shelves (context) - Machines, Release - 1995
3 Evolving 3d morphology and behavior by competition (context) - Kauffman - 1994
1 some studies of machine learning using the game of checkers (context) - by, errors et al. - 1959
1 and Crutchfield (context) - Mitchell, Hraber - 1993
1 Adaptation towards the edge of chaos (context) - edge, chaos et al. - 1988
1 Echoing emergence (context) - Holland - 1994
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.demo.cs.brandeis.edu/papers/long.html): More
A Gradient Descent Method for a Neural Fractal Memory - Melnik, Pollack (1998) (Correct)
Co-evolutionary Learning: Machines and Humans Schooling Together - Sklar (1998) (Correct)
A Scalable Divide-and-Conquer Parallel Algorithm for Finite.. - Mou, Ficici (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