QuickSearch:   Number of matching entries: 0.

AuthorTitleYearJournal/ProceedingsReftypeDOI/URL
Amant, R. S. & Young, R. M. Links: artificial intelligence and interactive entertainment

[BibTeX]

 2001 Intelligence   article DOI  
BibTeX: 
@article{378120,
  author = {Robert St. Amant and R. Michael Young},
  title = {Links: artificial intelligence and interactive entertainment},
  journal = {Intelligence},
  publisher = {ACM Press},
  year = {2001},
  volume = {12},
  number = {2},
  pages = {17--19},
  doi = {http://doi.acm.org/10.1145/378116.378120}
}
Cazangi, R. R., Zuben, F. J. V. & Figueiredo, M. F. Autonomous navigation system applied to collective robotics with ant-inspired communication

[Abstract] [BibTeX]

 2005 GECCO '05: Proceedings of the 2005 conference on Genetic and evolutionary computation   article DOI  
Abstract: Research in collective robotics is motivated mainly by the possibility of achieving an efficient solution to multi-objective navigation tasks when multiple robots are employed, instead of a single robot. Several approaches have already been tried in multi-robot systems, but the bio-inspired ones are the most frequent. This paper proposes to augment an autonomous navigation system based on learning classifier systems for using in collective robotics, introducing an inter-robot communication mechanism inspired by ant stigmergy, with each robot acting independently and cooperatively. The navigation system has no innate basic behavior and all knowledge necessary to compose the decision-making artifact is evolved as a function of the environmental feedback only, during navigation. Repulsive and/or attractive pheromone trails are produced by the robots along navigation, following very simple rules. Basically, each robot has to perform obstacle avoidance and target search, and the status of the pheromone level at the position currently occupied by each robot will influence the coordination of the two fundamental behaviors. Experiments are performed in simulation, with comparative results indicating that the presence of the pheromone trails is responsible for significant improvements in the capture rate and in the length of the route adopted by each robot.
BibTeX: 
@article{1068026,
  author = {Renato Reder Cazangi and Fernando J. Von Zuben and Maur\'{\i}cio F. Figueiredo},
  title = {Autonomous navigation system applied to collective robotics with ant-inspired communication},
  booktitle = {GECCO '05: Proceedings of the 2005 conference on Genetic and evolutionary computation},
  publisher = {ACM Press},
  year = {2005},
  pages = {121--128},
  doi = {http://doi.acm.org/10.1145/1068009.1068026}
}
Conitzer, V. & Sandholm, T. Communication complexity as a lower bound for learning in games

[BibTeX]

 2004 ICML '04: Proceedings of the twenty-first international conference on Machine learning   article DOI  
BibTeX: 
@article{1015351,
  author = {Vincent Conitzer and Tuomas Sandholm},
  title = {Communication complexity as a lower bound for learning in games},
  booktitle = {ICML '04: Proceedings of the twenty-first international conference on Machine learning},
  publisher = {ACM},
  year = {2004},
  pages = {24},
  doi = {http://doi.acm.org/10.1145/1015330.1015351}
}
Freund, Y. & Schapire, R. E. Experiments with a New Boosting Algorithm

[BibTeX]

 1996 International Conference on Machine Learning   article URL  
BibTeX: 
@article{freund96experiments,
  author = {Yoav Freund and Robert E. Schapire},
  title = {Experiments with a New Boosting Algorithm},
  booktitle = {International Conference on Machine Learning},
  year = {1996},
  pages = {148-156},
  url = {citeseer.ist.psu.edu/article/freund96experiments.html}
}
Kaelbling, L. P., Littman, M. L. & Moore, A. P. Reinforcement Learning: A Survey

[Abstract] [BibTeX]

 1996 Journal of Artificial Intelligence Research   article URL  
Abstract: This paper surveys the field of reinforcement learning from a

computer-science perspective.

It is written to be accessible to researchers familiar with machine

learning. Both

the historical basis of the field and a broad selection of current

work are summarized.

Reinforcement learning is the problem faced by an agent that learns

behavior through

trial-and-error interactions with a dynamic environment. The work

described here has a

resemblance to work in psychology, but differs considerably in the

details and in the use

of the word "reinforcement." The paper discusses central

issues of reinforcement learning,

including trading off exploration and exploitation, establishing the

foundations of the field

via Markov decision theory, learning from delayed reinforcement,

constructing empirical

models to accelerate learning, making use of generalization and

hierarchy, and coping with

hidden state. It concludes with a survey of some implemented systems

and an assessment

of the practical utility...
BibTeX: 
@article{kaelbling96reinforcement,
  author = {Leslie Pack Kaelbling and Michael L. Littman and Andrew P. Moore},
  title = {Reinforcement Learning: A Survey},
  journal = {Journal of Artificial Intelligence Research},
  year = {1996},
  volume = {4},
  pages = {237-285},
  url = {citeseer.ist.psu.edu/article/kaelbling96reinforcement.html}
}
Kalles, D. & Kanellopoulos, P. On verifying game designs and playing strategies using reinforcement learning

[BibTeX]

 2001 SAC '01: Proceedings of the 2001 ACM symposium on Applied computing   article DOI  
BibTeX: 
@article{372204,
  author = {Dimitrios Kalles and Panagiotis Kanellopoulos},
  title = {On verifying game designs and playing strategies using reinforcement learning},
  booktitle = {SAC '01: Proceedings of the 2001 ACM symposium on Applied computing},
  publisher = {ACM},
  year = {2001},
  pages = {6--11},
  doi = {http://doi.acm.org/10.1145/372202.372204}
}
Laird, J. E. Using a Computer Game to Develop Advanced AI

[Abstract] [BibTeX]

 2001 Computer   article URL  
Abstract: s games, from detailed indoor rooms and corridors to vast outdoor landscapes. These games populate the environments with both human and computer controlled characters, making them a rich laboratory for artificial intelligence research into developing intelligent and social autonomous agents. Indeed, computer games offer a fitting subject for serious academic study, undergraduate education, and graduate student and faculty research. Creating and efficiently rendering these environments...
BibTeX: 
@article{laird01using,
  author = {John E. Laird},
  title = {Using a Computer Game to Develop Advanced {AI}},
  journal = {Computer},
  year = {2001},
  volume = {34},
  number = {7},
  pages = {70--75},
  url = {citeseer.ist.psu.edu/laird01using.html}
}
Lassabe, N., Sanchez, S., Luga, H. & Duthen, Y. Genetically programmed strategies for chess endgame

[BibTeX]

 2006 GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation   article DOI  
BibTeX: 
@article{1144144,
  author = {Nicolas Lassabe and St\'{e}phane Sanchez and Herv\'{e}e Luga and Yves Duthen},
  title = {Genetically programmed strategies for chess endgame},
  booktitle = {GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation},
  publisher = {ACM},
  year = {2006},
  pages = {831--838},
  doi = {http://doi.acm.org/10.1145/1143997.1144144}
}
Livingstone, D. Turing's test and believable AI in games

[BibTeX]

 2006 Comput. Entertain.   article DOI  
BibTeX: 
@article{1111303,
  author = {Daniel Livingstone},
  title = {Turing's test and believable AI in games},
  journal = {Comput. Entertain.},
  publisher = {ACM},
  year = {2006},
  volume = {4},
  number = {1},
  pages = {6},
  doi = {http://doi.acm.org/10.1145/1111293.1111303}
}
McDowell, J. J., Soto, P. L., Dallery, J. & Kulubekova, S. A computational theory of adaptive behavior based on an evolutionary reinforcement mechanism

[Abstract] [BibTeX]

 2006 GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation   article DOI  
Abstract: Two mathematical and two computational theories from the field of human and animal learning are combined to produce a more general theory of adaptive behavior. The cornerstone of this theory is an evolutionary algorithm for reinforcement learning that instantiates the idea that behavior evolves in response to selection pressure from the environment in the form of reinforcement. The evolutionary reinforcement algorithm, along with its associated equilibrium theory, are combined with a mathematical theory of conditioned reinforcement and a computational theory of associative learning that together solve the problem of credit assignment in a biologically plausible way. The result is a biologically-inspired computational theory that enables an artificial organism to adapt continuously to changing environmental conditions and to generate adaptive state-action sequences.
BibTeX: 
@article{1144028,
  author = {J. J McDowell and Paul L. Soto and Jesse Dallery and Saule Kulubekova},
  title = {A computational theory of adaptive behavior based on an evolutionary reinforcement mechanism},
  booktitle = {GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation},
  publisher = {ACM Press},
  year = {2006},
  pages = {175--182},
  doi = {http://doi.acm.org/10.1145/1143997.1144028}
}
Miikkulainen, R. Evolving neural networks

[Abstract] [BibTeX]

 2007 GECCO '07: Proceedings of the 2007 GECCO conference companion on Genetic and evolutionary computation   article DOI  
Abstract: Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional(e.g. value-function based) methods, neuroevolution is especially strong in domains where the state of the world is not fully known: the state can be disambiguated through recurrency, and novel situations handled through pattern matching. In this tutorial, we will review (1)neuroevolution methods that evolve fixed-topology networks, network topologies, and network construction processes, (2) ways of combining traditional neural network learning algorithms with evolutionary methods, and (3) applications of neuroevolution to game playing, robot control, resource optimization, and cognitive science.
BibTeX: 
@article{1274119,
  author = {Risto Miikkulainen},
  title = {Evolving neural networks},
  booktitle = {GECCO '07: Proceedings of the 2007 GECCO conference companion on Genetic and evolutionary computation},
  publisher = {ACM Press},
  year = {2007},
  pages = {3415--3434},
  doi = {http://doi.acm.org/10.1145/1274000.1274119}
}
Norouzi, A., Ziabary, S. M. M., Mousakhani, M. & Shoaei, S. M. R. Semi-human instinctive artificial intelligence (SHI-AI)

[Abstract] [BibTeX]

 2006 PCAR '06: Proceedings of the 2006 international symposium on Practical cognitive agents and robots   article DOI  
Abstract: Providing robots (or any other intelligent embedded system) with manlike instincts will bring major issues of today artificial intelligence out of a deadlock. This paper proposes a nondeterministic decision making theory based on Semi Human Instincts implemented by learned potential fields, using neural networks and fuzzy logic offline and online learning algorithms, which enable the agent to perform in anonymous, dynamic and non-deterministic environments. SHI-AI is like a newly born baby who uses his/her instincts and will gradually become more and more intelligent as the brain learns more about its environment. The use of a new world modeling method called ARPL in SHI-AI enables the agent to perform better within anonymous environments where positioning is an important and complex issue.
BibTeX: 
@article{1232446,
  author = {Asadollah Norouzi and S. Mohammad Mohammadzadeh Ziabary and Morteza Mousakhani and S. Mohammad Reza Shoaei},
  title = {Semi-human instinctive artificial intelligence (SHI-AI)},
  booktitle = {PCAR '06: Proceedings of the 2006 international symposium on Practical cognitive agents and robots},
  publisher = {ACM Press},
  year = {2006},
  pages = {153--164},
  doi = {http://doi.acm.org/10.1145/1232425.1232446}
}
Roy, A. Artificial neural networks: a science in trouble

[Abstract] [BibTeX]

 2000 SIGKDD Explor. Newsl.   article DOI  
Abstract: This article points out some very serious misconceptions about the brain in connectionism and artificial neural networks. Some of the connectionist ideas have been shown to have logical flaws, while others are inconsistent with some commonly observed human learning processes and behavior. For example, the connectionist ideas have absolutely no provision for learning from stored information, something that humans do all the time. The article also argues that there is definitely a need for some new ideas about the internal mechanisms of the brain. It points out that a very convincing argument can be made for a "control theoretic" approach to understanding the brain. A "control theoretic" approach is actually used in all connectionist and neural network algorithms and it can also be justified from recent neurobiological evidence. A control theoretic approach proposes that there are subsystems within the brain that control other subsystems. Hence a similar approach can be taken in constructing learning algorithms and other intelligent systems.
BibTeX: 
@article{846192,
  author = {Asim Roy},
  title = {Artificial neural networks: a science in trouble},
  journal = {SIGKDD Explor. Newsl.},
  publisher = {ACM Press},
  year = {2000},
  volume = {1},
  number = {2},
  pages = {33--38},
  doi = {http://doi.acm.org/10.1145/846183.846192}
}
Stuart Russell, P. N. Artificial Intelligence: A Modern Approach

[BibTeX]

 1995   book  
BibTeX: 
@book{,
  author = {Stuart Russell, Peter Norvig},
  title = {Artificial Intelligence: A Modern Approach},
  publisher = {Prentice Hall},
  year = {1995}
}
Taylor, M. E., Whiteson, S. & Stone, P. Comparing evolutionary and temporal difference methods in a reinforcement learning domain

[Abstract] [BibTeX]

 2006 GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation   article DOI  
Abstract: Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical comparisons have been conducted, there are no general guidelines describing the methods' relative strengths and weaknesses. This paper presents the results of a detailed empirical comparison between a GA and a TD method in Keepaway, a standard RL benchmark domain based on robot soccer. In particular, we compare the performance of NEAT [19], a GA that evolves neural networks, with Sarsa [16, 17], a popular TD method. The results demonstrate that NEAT can learn better policies in this task, though it requires more evaluations to do so. Additional experiments in two variations of Keepaway demonstrate that Sarsa learns better policies when the task is fully observable and NEAT learns faster when the task is deterministic. Together, these results help isolate the factors critical to the performance of each method and yield insights into their general strengths and weaknesses.
BibTeX: 
@article{1144202,
  author = {Matthew E. Taylor and Shimon Whiteson and Peter Stone},
  title = {Comparing evolutionary and temporal difference methods in a reinforcement learning domain},
  booktitle = {GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computation},
  publisher = {ACM Press},
  year = {2006},
  pages = {1321--1328},
  doi = {http://doi.acm.org/10.1145/1143997.1144202}
}
Towell, G. G. & Shavlik, J. W. Knowledge-Based Artificial Neural Networks

[Abstract] [BibTeX]

 1994 Artificial Intelligence   article URL  
Abstract: Hybrid learning methods use theoretical knowledge of a domain and a

set of classified examples

to develop a method for accurately classifying examples not seen

during training. The challenge of

hybrid learning systems is to use the information provided by one

source of information to offset

information missing from the other source. By so doing, a hybrid

learning system should learn

more effectively than systems that use only one of the information

sources. Kbann(Knowledge-

Based Artificial Neural Networks) is a hybrid learning system built

on top of connectionist learning

techniques. It maps problem-specific "domain theories",

represented in propositional logic, into

neural networks and then refines this reformulated knowledge using

backpropagation. Kbann is

evaluated by extensive empirical tests on two problems from molecular

biology. Among other

results, these tests show that the networks created by Kbann

generalize better than a wide variety

of learning systems, as well as several...
BibTeX: 
@article{towell94knowledgebased,
  author = {Geoffrey G. Towell and Jude W. Shavlik},
  title = {Knowledge-Based Artificial Neural Networks},
  journal = {Artificial Intelligence},
  year = {1994},
  volume = {70},
  number = {1-2},
  pages = {119-165},
  url = {citeseer.ist.psu.edu/article/towell94knowledgebased.html}
}
Wang, F. & Mckenzie, E. A multi-agent based evolutionary artificial neural network for general navigation in unknown environments

[BibTeX]

 1999 AGENTS '99: Proceedings of the third annual conference on Autonomous Agents   article DOI  
BibTeX: 
@article{301182,
  author = {Fang Wang and Eric Mckenzie},
  title = {A multi-agent based evolutionary artificial neural network for general navigation in unknown environments},
  booktitle = {AGENTS '99: Proceedings of the third annual conference on Autonomous Agents},
  publisher = {ACM Press},
  year = {1999},
  pages = {154--159},
  doi = {http://doi.acm.org/10.1145/301136.301182}
}
Whiteson, S. & Stone, P. Evolutionary Function Approximation for Reinforcement Learning

[Abstract] [BibTeX]

 2006 J. Mach. Learn. Res.   article  
Abstract: Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning tasks, TD methods require a function approximator to represent the value function. However, using function approximators requires manually making crucial representational decisions. This paper investigates evolutionary function approximation, a novel approach to automatically selecting function approximator representations that enable efficient individual learning. This method evolves individuals that are better able to learn. We present a fully implemented instantiation of evolutionary function approximation which combines NEAT, a neuroevolutionary optimization technique, with Q-learning, a popular TD method. The resulting NEAT+Q algorithm automatically discovers effective representations for neural network function approximators. This paper also presents on-line evolutionary computation, which improves the on-line performance of evolutionary computation by borrowing selection mechanisms used in TD methods to choose individual actions and using them in evolutionary computation to select policies for evaluation. We evaluate these contributions with extended empirical studies in two domains: 1) the mountain car task, a standard reinforcement learning benchmark on which neural network function approximators have previously performed poorly and 2) server job scheduling, a large probabilistic domain drawn from the field of autonomic computing. The results demonstrate that evolutionary function approximation can significantly improve the performance of TD methods and on-line evolutionary computation can significantly improve evolutionary methods. This paper also presents additional tests that offer insight into what factors can make neural network function approximation difficult in practice.
BibTeX: 
@article{1248578,
  author = {Shimon Whiteson and Peter Stone},
  title = {Evolutionary Function Approximation for Reinforcement Learning},
  journal = {J. Mach. Learn. Res.},
  publisher = {MIT Press},
  year = {2006},
  volume = {7},
  pages = {877--917}
}
Zhang, D. & Tsai, J. Machine learning and software engineering

[Abstract] [BibTeX]

 2002 Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings. 14th IEEE International Conference on   inproceedings  
Abstract: Machine learning deals with the issue of how to build programs that improve their performance at some task through experience. Machine learning algorithms have proven to be of great practical value in a variety of application domains. Not surprisingly, the field of software engineering turns out to be a fertile ground where many software development and maintenance tasks could be formulated as learning problems and approached in terms of learning algorithms. This paper deals with the subject of applying machine learning methods to so are engineering. In the paper, we first provide the characteristics and applicability of some frequently utilized machine learning algorithms. We then summarize and analyze the existing work and discuss some general issues in this niche area. Finally we offer some guidelines on applying machine learning methods to software engineering tasks.
BibTeX: 
@inproceedings{Zhang2002,
  author = {Zhang, Du and Tsai, J.J.P.},
  title = {Machine learning and software engineering},
  booktitle = {Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings. 14th IEEE International Conference on},
  year = {2002},
  pages = {22--29}
}

Created by JabRef on 04/11/2007.