📄 http:^^www.cs.wisc.edu^~shavlik^ml95w1^
字号:
Date: Tue, 05 Nov 1996 00:40:53 GMTServer: NCSA/1.5Content-type: text/htmlLast-modified: Wed, 28 Jun 1995 19:13:44 GMTContent-length: 8252<HTML><HEAD><TITLE>Proceedings: ML95 Workshop on `Agents that Learn from Other Agents'</TITLE></HEAD><BODY><H1>Agents that Learn from Other Agents</H1>This is the on-line proceedings of theworkshop on <EM>Agents that Learn from Other Agents</EM>held as part of the <!WA0><A HREF="http://www.eecs.wsu.edu/~schlimme/ml95.html">1995 International Machine Learning Conference</A>. Led by an invited talk by <!WA1><A HREF="http://www.cs.cmu.edu:8001/afs/cs.cmu.edu/user/mitchell/ftp/tomhome.html">Tom Mitchell</A> of Carnegie-Mellon University,eleven reports about current research on this topic were presented.<P><H2>Introduction</H2>There has been a growing trend in machine learning toward learningmethods that involve interacting with other agents. One such interaction is via advice-taking (Suddarth & Holden 1991), which may well turn out to be themost efficient method for building software-agent architectures. Instruction issteadily increasing in popularity as a method for agent learning (e.g., Gordon & Subramanian 1993, Huffman & Laird 1993, Lin 1993, Maclin & Shavlik 1994,Noelle & Cotrell 1994, Tecuci, Hieb, Hille, & Pullen 1994).Meanwhile, there is alsoan active interest in agents that learn from observation (e.g., Iba 1991, Lin 1993),as well as agents that communicate and learn from each other (e.g., Etzioni & Weld 1994, Lashkari, Metral, & Maes 1994, Tan 1993). Furthermore, in the COLT community there have been a number of paperson team learning (e.g., Daley, Kalyanasundaram, & Velauthapillai 1993).For these reasons, the main focus ofthis workshop was on learning from instruction or observation, rather than theenvironment. The instructors might be humans or other automated agents.(References to the above-mentioned articles appear below.)<P><H2>Organizing Committee</H2> <UL> <LI> <!WA2><A HREF="http://www.aic.nrl.navy.mil/~gordon/"> Diana Gordon</A>, Naval Research Laboratory (chair) <LI> <!WA3><A HREF="http://www.cs.pitt.edu/~daley/"> Robert Daley</A>, University of Pittsburgh <LI> <!WA4><A HREF="http://www.cs.wisc.edu/~shavlik/"> Jude Shavlik</A>, University of Wisconsin <LI> <!WA5><A HREF="http://www.cs.cornell.edu/Info/Faculty/Devika_Subramanian.html"> Devika Subramanian</A>, Cornell University <LI> <!WA6><A HREF="http://www.cs.gmu.edu/faculty/tecuci.html"> Gheorghe Tecuci</A>, George Mason University and Romanian Academy </UL><H2>Proceedings</H2>(The schedule is currently <!WA7><A HREF="http://www.cs.wisc.edu/~shavlik/ml95w1/schedule.html">on-line</A>.)<P><H3>Theory of Team Learning</H3> <UL> <LI> <!WA8><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/jain.ps.gz"> <EM>Team learning of formal languages</EM></A>, by Sanjay Jain, National University of Singapore, and Arun Sharma, University of New South Wales. </UL><H3> Learning from Instruction </H3> <UL> <LI> <!WA9><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/pearson.ps.gz"> <EM>Combining learning from instruction with recovery from incorrect knowledge</EM></A>, by <!WA10><A HREF="http://ai.eecs.umich.edu/people/douglasp/homepage.html"> Douglas Pearson</A>, University of Michigan, and <!WA11><A HREF="http://ai.eecs.umich.edu/people/huffman/huffman.html"> Scott Huffman</A>, Price Waterhouse. <LI> <!WA12><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/grosof.ps.gz"> <EM>Conflict resolution in advice taking and instruction for learning agents</EM></A>, by Benjamin Grosof, <!WA13><A HREF="http://www.watson.ibm.com">IBM Watson Research</A>. <LI> <!WA14><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/clouse.ps.gz"> <EM>Learning from an automated training agent</EM></A>, by Jeffrey Clouse, University of Massachusetts. <LI> <EM>Learning from instruction and experience in competitive situations</EM>, by <!WA15><A HREF="http://www.cs.wisc.edu/~shavlik"> Jude Shavlik</A> and <!WA16><A HREF="http://www.cs.wisc.edu/~maclin/maclin.html"> Richard Maclin</A>, University of Wisconsin. </UL><H3> Learning from Observation </H3> <UL> <LI> <!WA17><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/asada.ps.gz"> <EM>Agents that learn from other competitive agents</EM></A>, by Minoru Asada, Eiji Uchibe, and Koh Hosoda, Osaka University. <LI> <!WA18><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/payne.ps.gz"> <EM>Experience with rule induction and k-nearest neighbour methods for interface agents that learn</EM></A>, by <!WA19><A HREF="http://www.csd.abdn.ac.uk/~terry/terry.html"> Terry Payne</A>, <!WA20><A HREF="http://www.csd.abdn.ac.uk/~pedwards/pedwards.html"> Peter Edwards</A>, and <!WA21><A HREF="http://www.csd.abdn.ac.uk/~clg/clg.html"> Claire Green</A>, University of Aberdeen. </UL><H3> Knowledge Acquisition and Refinement </H3> <UL> <LI> <!WA22><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/gil.ps.gz"> <EM>Acquiring knowledge from users in a reflective architecture</EM></A>, by Yolanda Gil, Information Sciences Institute / USC. <LI> <!WA23><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/davies.ps"> <EM>Distributed learning: An agent-based approach to data-mining</EM></A>, by <!WA24><A HREF="http://www.csd.abdn.ac.uk/~wdavies/wdavies.html"> Winton Davies</A> and <!WA25><A HREF="http://www.csd.abdn.ac.uk/~pedwards/pedwards.html"> Peter Edwards</A>, University of Aberdeen. <LI> <!WA26><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/ml95w1/byrne.ps.gz"> <EM>Refining the knowledge of multiple agents</EM></A>, by <!WA27><A HREF="http://www.csd.abdn.ac.uk/~byrne/byrne.html"> Ciara Byrne</A> and <!WA28><A HREF="http://www.csd.abdn.ac.uk/~pedwards/pedwards.html"> Peter Edwards</A>, University of Aberdeen. </UL><HR><H2>Bibliography for the Introduction</H2> <UL> <LI> S. Suddarth & A. Holden. Symbolic-neural systems and the use of hints in developing complex systems. <EM>International Journal of Man-Machine Studies</EM>, <EM>35</EM>:291-311, 1991. <LI> D. Gordon & D. Subramanian. <!WA29><A HREF="ftp://ftp.aic.nrl.navy.mil/pub/gordon/selected_papers/informatica93.ps"> A multistrategy learning scheme for agent knowledge acquisition.</A> <EM>Informatica 17</EM>:331-346, 1993. <LI> S. Huffman & J. Laird. Learning procedures from interactive natural language instructions. <EM>Procs: 1993 Machine Learning Conf.</EM> <LI> L. Lin. Scaling up reinforcement learning for robot control. <EM>Procs: 1993 Machine Learning Conf.</EM> <LI> G. Tecuci, M. Hieb, D. Hille, & J. Pullen. Building adaptive autonomous agents for adversarial domains. <EM>Procs: AAAI-94 Fall Symposium</EM>. <LI> R. Maclin & J. Shavlik. <!WA30><A HREF="ftp://ftp.cs.wisc.edu/machine-learning/shavlik-group/maclin.aaai94.ps"> Incorporating advice into agents that learn from reinforcements</A>. <EM>Procs: AAAI-94</EM>. <LI> D. Noelle & G. Cottrell. Integrating induction and instruction: Connectionist advice taking. <EM>Procs: AAAI-94</EM>. <LI> W. Iba. Learning to classify observed motor behavior. <EM>Procs: IJCAI-91</EM>. <LI> O. Etzioni & D. Weld. A softbot-based interface to the Internet. <EM>Communications of the ACM, 37(7)</em>, special issue on Intelligent Agents, 1994. <LI> Y. Lashkari, M. Metral, & P. Maes. Collaborative interfact agents. <EM>Procs: AAAI-94</EM>. <LI> M. Tan. Multi-agent reinforcement learning: Independent vs. cooperative agents. <EM>Procs: 1993 Machine Learning Conf</EM>. <LI> R. Daley, B. Kalyanasundaram, & M. Velauthapillai. Capabilities of fallible finite learning. <EM>Procs: COLT-93</EM>. </UL><HR>Last modified: Fri Jun 16 16:45:58 1995 by Jude Shavlik<ADDRESS> <!WA31><A HREF="mailto:shavlik@cs.wisc.edu">shavlik@cs.wisc.edu</A></ADDRESS><HR></BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -