Adaptation and Learning in Multi-Agent Systems: Some Remarks and a Bibliography

In the last years the topic of adaptation and learning in multi-agent systems has gained increasing attention in Artificial Intelligence. This article is intended to provide a compact, introductory and motivational guide to this topic. The article consists of two sections. In the first section,“Remarks”, the range and complexity of this topic is outlined by taking a general look at the concept of multi-agent systems and at the notion of adaptation and learning in these systems. This includes a description of key dimensions for classifying multi-agent systems, as well as a description of key criteria for characterizing single-agent and multi-agent learning as the two principal categories of learning in multiagent systems. In the second section, “Bibliography”, an extensive list of pointers to relevant and related work on multi-agent learning done in (Distributed) Artificial Intelligence, economics, and other disciplines is provided.

[1]  M. Matarić.  Learning to Behave Socially , 1994 .

[2]  Daniel A. Levinthal,et al.  ABSORPTIVE CAPACITY: A NEW PERSPECTIVE ON LEARNING AND INNOVATION , 1990 .

[3]  H. Simon,et al.  Bounded Rationality and Organizational Learning , 1991 .

[4]  R. Revans.  Action Learning: New Techniques for Management , 1980 .

[5]  Pattie Maes.  Social Interface Agents: Acquiring Competence by Learning from Users and other Agents , 1994 .

[6]  Daniel A. Levinthal,et al.  Learning from Experience in Organizations , 1985 .

[7]  Linda Argote,et al.  Organizational Learning Curves: A Method for Investigating Intra-Plant Transfer of Knowledge Acquired Through Learning by Doing , 1991 .

[8]  Mark Humphrys.  W-learning: Competition among selfish Q-learners , 1995 .

[9]  K. Weick.  The Nontraditional Quality of Organizational Learning , 1991 .

[10]  Michael X Cohen,et al.  A Garbage Can Model of Organizational Choice. , 1972 .

[11]  J. PearsonArti.  Combining learning from instruction with recovery from incorrectknowledgeDouglas , 1995 .

[12]  Gerhard Weiß,et al.  Action selection and learning in multi-agent environments , 1993, Forschungsberichte, TU Munich.

[13]  Lynne E. Parker,et al.  Adaptive action selection for cooperative agent teams , 1993 .

[14]  S. Mezias,et al.  An Organizational Learning Model of Convergence and Reorientation , 1992 .

[15]  Arun Sharma,et al.  Finite learning by a “team” , 1990, COLT '90.

[16]  E. Feigenbaum,et al.  Computers and Thought , 1963 .

[17]  Moshe Tennenholtz,et al.  On Social Laws for Artificial Agent Societies: Off-Line Design , 1995, Artif. Intell..

[18]  Alexander Renkl,et al.  A plea for “more local” theories of cooperative learning , 1992 .

[19]  Ming Tan,et al.  Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents , 1997, ICML.

[20]  Sandip Sen,et al.  Learning to Coordinate without Sharing Information , 1994, AAAI.

[21]  C. B. Schoonhoven.  Institutionalizing Innovation: A Study of Organizational Learning Systems , 1982 .

[22]  Gustavo Stubrich.  The Fifth Discipline: The Art and Practice of the Learning Organization , 1993 .

[23]  Mary Anne Devanna,et al.  Strategic Human Resource Management , 1984 .

[24]  C. Argyris.  Reasoning, learning, and action : individual and organizational , 1982 .

[25]  Bruce K. Friesen,et al.  The learning organization , 1992 .

[26]  Salvatore J. Stolfo,et al.  Toward Multi-Strategy Parallel & Distributed Learning in Sequence Analysis , 1993, ISMB.

[27]  B. Garratt.  Creating a learning organisation : a guide to leadership, learning and development , 1990 .

[28]  A LevinthalDaniel.  Organizational Adaptation and Environmental Selection-Interrelated Processes of Change , 1991 .

[29]  Peter Edwards,et al.  Collaborating to Refine Knowledge , 1995 .

[30]  Hans Spada,et al.  Learning in Humans and Machines: Towards an Interdisciplinary Learning Science , 1995 .

[31]  Michael N. Huhns,et al.  Distributed artificial intelligence: vol. 2 , 1989 .

[32]  Peter Edwards,et al.  Distributed Learning: An Agent-Based Approach to Data-Mining , 1995 .

[33]  Savvas A. Katsikides.  Informatics, organization and society , 1994 .

[34]  Michael L. Littman,et al.  Markov Games as a Framework for Multi-Agent Reinforcement Learning , 1994, ICML.

[35]  Moshe Tennenholtz,et al.  Adaptive Load Balancing: A Study in Multi-Agent Learning , 1994, J. Artif. Intell. Res..

[36]  Gunnar Pautzke,et al.  Die Evolution der organisatorischen Wissensbasis , 1989 .

[37]  R. Daft,et al.  How Organizations Learn: A Communication Framework. , 1986 .

[38]  Daniel A. Levinthal.  Organizational Adaptation and Environmental Selection-Interrelated Processes of Change , 1991 .

[39]  James G. March,et al.  Adaptive Coordination of a Learning Team , 1987 .

[40]  Robert H. Crites,et al.  Multiagent reinforcement learning in the Iterated Prisoner's Dilemma. , 1996, Bio Systems.

[41]  Michael N. Huhns,et al.  Chapter 9 – DAI for Document Retrieval: The MINDS Project , 1987 .

[42]  Luís Torgo,et al.  Panel: Learning in Distributed Systems and Multi-Agent Environments , 1991, EWSL.

[43]  Moshe Tennenholtz,et al.  On Social Laws for Arti cial AgentSocieties : OLine Design , 1995 .

[44]  Cristiano Castelfranchi,et al.  Artificial Social Systems , 1994 .

[45]  Louis E. Yelle.  THE LEARNING CURVE: HISTORICAL REVIEW AND COMPREHENSIVE SURVEY , 1979 .

[46]  Michael L. Littman,et al.  A Distributed Reinforcement Learning Scheme for Network Routing , 1993 .

[47]  Sandip Sen,et al.  Multi-Agent Learning in Non-Cooperative Domains , 1994, AAAI.

[48]  S. Mezias,et al.  MANAGING DISCONTINUOUS CHANGE: A SIMULATION STUDY OF ORGANIZATIONAL LEARNING AND ENTREPRENEURSHIP , 1990 .

[49]  Sati S. Sian,et al.  Extending Learning to Multiple Agents: Issues and a Model for Multi-Agent Machine Learning (MA-ML) , 1991, EWSL.

[50]  Salvatore J. Stolfo,et al.  Toward parallel and distributed learning by meta-learning , 1993 .

[51]  Andrew Pettigrew,et al.  The organizational life cycle : issues in the creation, transformation, and decline of organizations , 1981 .

[52]  Gerhard Weiß.  Distributed Machine Learning , 1995, DISKI.

[53]  J. Brown,et al.  Organizational Learning and Communities-of-Practice: Toward a Unified View of Working, Learning, and Innovation , 1991 .

[54]  Stephen Muggleton,et al.  Learning to Relate Terms in a Multiple Agent Environment , 1991, EWSL.

[55]  Victor R. Lesser,et al.  Cooperative Learning over Composite Search Spaces: Experiences with a Multi-Agent Design System , 1996, AAAI/IAAI, Vol. 1.

[56]  Gerhard Weiss,et al.  Some Studies in Distributed Machine Learning and Organizational Design , 1994 .

[57]  M. Masuch,et al.  Beyond Garbage Cans: An AI Model of Organizational Choice , 1989 .

[58]  R. D. Bonnell,et al.  Learning for distributed artificial intelligence systems , 1991, [1991 Proceedings] The Twenty-Third Southeastern Symposium on System Theory.

[59]  Moshe Tennenholtz,et al.  On computational social laws for dynamic non-homogeneous social structures , 1995, J. Exp. Theor. Artif. Intell..

[60]  G. Huber.  Organizational Learning: The Contributing Processes and the Literatures , 1991 .

[61]  P. Shrivastava.  A TYPOLOGY OF ORGANIZATIONAL LEARNING SYSTEMS , 1983 .

[62]  Bala Kalyanasundaram,et al.  Breaking the probability ½ barrier in FIN-type learning , 1992, COLT '92.

[63]  Arun Sharma,et al.  Computational Limits on Team Identification of Languages , 1996, Inf. Comput..

[64]  Riyaz Sikora,et al.  A double-layered learning approach to acquiring rules for financial classification / 1693 , 1990 .

[65]  Arun Sharma,et al.  Probability is more powerful than team for language identification from positive data , 1993, COLT '93.

[66]  Michael J. Shaw,et al.  A distributed problem-solving approach to inductive learning , 1990 .

[67]  Pat Langley,et al.  Elements of Machine Learning , 1995 .

[68]  Nancy M. Dixon.  ACTION LEARNING, ACTION SCIENCE AND LEARNING NEW SKILLS , 1990 .

[69]  R. Osborn,et al.  Handbook of Organizational Design. Vol. 1: Adapting Organizations to Their Environments. , 1982 .

[70]  P. Dillenbourg,et al.  The evolution of research on collaborative learning , 1996 .

[71]  P. R. Laughlin.  Collective induction: Group performance, social combination processes, and mutual majority and minority influence. , 1988 .

[72]  W. Dill,et al.  ORGANIZATIONAL LEARNING: OBSERVATIONS TOWARD A THEORY, , 1965 .

[73]  Pierre Dillenbourg,et al.  The distribution of pedagogical roles in a Multi-agent Learning Environment , 1993, Lessons from Learning.

[74]  Victor Lesser,et al.  Learning Organizational Roles in a Heterogeneous Multi-agent System , 1995 .

[75]  M. Dodgson.  Organizational Learning: A Review of Some Literatures , 1993 .

[76]  Foster J. Provost,et al.  Distributed Machine Learning: Scaling Up with Coarse-grained Parallelism , 1994, ISMB.

[77]  Michael X Cohen.  Individual Learning and Organizational Routine: Emerging Connections , 1991 .

[78]  V. Marsick.  Learning in the workplace , 1987 .

[79]  Cristiano Castelfranchi,et al.  From Reaction to Cognition , 1993, Lecture Notes in Computer Science.

[80]  Paul S. Adler,et al.  Shared learning , 1990 .

[81]  Nancy M. Dixon,et al.  Organizational Learning: A Review of the Literature with Implications for HRD Professionals. , 1992 .

[82]  B. Hedberg.  How Organizations Learn and Unlearn , 1981 .

[83]  E. Grochla.  Handwörterbuch der Organisation , 1969 .

[84]  P. Nystrom,et al.  To Avoid Organizational Crises, Unlearn , 1984 .

[85]  Larry M. Stephens,et al.  Learning in multiagent systems , 1995 .

[86]  Daniel H. Kim.  The Link between individual and organizational learning , 1997 .

[87]  Thomas Sattelberger.  Die lernende Organisation : Konzepte für eine neue Qualität der Unternehmensentwicklung , 1996 .

[88]  Leonard Pitt,et al.  Relations between probabilistic and team one-shot learners (extended abstract) , 1991, COLT '91.

[89]  Mahendran Velauthapillai.  Inductive inference with bounded number of mind changes , 1989, COLT '89.

[90]  Bala Kalyanasundaram,et al.  Capabilities of fallible FINite learning , 1993, COLT '93.

[91]  Carl H. Smith,et al.  Probability and Plurality for Aggregations of Learning Machines , 1987, Inf. Comput..

[92]  Michael L. Littman,et al.  Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach , 1993, NIPS.

[93]  J. Roschelle.  Learning by Collaborating: Convergent Conceptual Change , 1992 .

[94]  Marvin Minsky,et al.  Steps toward Artificial Intelligence , 1995, Proceedings of the IRE.

[95]  P. Chan,et al.  Toward multistrategy parallel and distributed learning in sequence analysis. , 1993, Proceedings. International Conference on Intelligent Systems for Molecular Biology.

[96]  Massimo Warglien,et al.  Artificial Intelligence in Organization and Management Theory , 1992 .

[97]  R. Duncan.  Organizational Learning : Implications for organizational design , 1979 .

[98]  Johannes M. Pennings,et al.  Organizational Strategy and Change: New Views on Formulating and Implementing Strategic Decisions. , 1986 .

[99]  Alan H. Bond,et al.  Distributed Artificial Intelligence , 1988 .

[100]  Johan P. Olsen,et al.  THE UNCERTAINTY OF THE PAST: ORGANIZATIONAL LEARNING UNDER AMBIGUITY* , 1975 .

[101]  Bala Kalyanasundaram,et al.  The power of probabilism in Popperian FINite learning , 1994, J. Exp. Theor. Artif. Intell..

[102]  Moshe Tennenholtz,et al.  Emergent Conventions in Multi-Agent Systems: Initial Experimental Results and Observations (Preliminary Report) , 1992, KR.

[103]  Bala Kalyanasundaram,et al.  Breaking the Probability 1/2 Barrier in FIN-Type Learning , 1995, J. Comput. Syst. Sci..

[104]  Victor Lesser,et al.  Learning Experiments in a Heterogeneous Multi-agent System , 1995 .

[105]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[106]  Leonard Pitt,et al.  A Characterization of Probabilistic Inference , 1984, FOCS.

[107]  Lewis J. Perelman.  The learning enterprise : adult learning human capital and economic development , 1984 .

[108]  S. Sian.  The Role Of Cooperation in Multi-Agent Learning , 1991 .

[109]  Leonard Pitt,et al.  Probabilistic inductive inference , 1989, JACM.

[110]  Thomas Sattelberger.  Die Lernende Organisation , 1991 .

[111]  Alan H. Bond,et al.  Readings in Distributed Artificial Intelligence , 1988 .

[112]  Our Special Correspondent.  The Organization of Science , 1915, Science.

[113]  Arun Sharma,et al.  Language Learning by a "Team" (Extended Abstract) , 1990, ICALP.

[114]  Arun Sharma,et al.  On Aggregating Teams of Learning Machines , 1995, Theor. Comput. Sci..

[115]  Edmund H. Durfee,et al.  Distributed Problem Solving and Multi-Agent Systems: Comparisons and Examples* , 1994 .

[116]  Richard Maclin.  Learning From Instruction And Experience: Methods For Incorporating Procedural Domain Theories Into , 1995 .

[117]  Carl H. Smith,et al.  The Power of Pluralism for Automatic Program Synthesis , 1982, JACM.

[118]  Yves Kodratoff,et al.  Machine Learning — EWSL-91 , 1991, Lecture Notes in Computer Science.

[119]  Arun Sharma,et al.  On Aggregating Teams of Learning Machines , 1993, ALT.

[120]  Gerhard Weiß,et al.  Distributed reinforcement learning , 1995, Robotics Auton. Syst..

[121]  Larry M. Stephens,et al.  MAGE: ADDITIONS TO THE AGE ALGORITHM FOR LEARNING IN MULTI-AGENT SYSTEMS , 1993 .

[122]  Nicholas V. Findler.  Distributed Control of Collaborating and Learning Expert Systems for Street Traffic Signals , 1991 .

[123]  Gerhard Weiss,et al.  Learning to Coordinate Actions in Multi-Agent-Systems , 1993, IJCAI.

[124]  Moshe Tennenholtz,et al.  Co-Learning and the Evolution of Social Acitivity , 1994 .

[125]  M. Easterby-Smith.  Creating a Learning Organisation , 1990 .

[126]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[127]  Terry R. Payne,et al.  Experience with Rule Induction and k-Nearest Neighbor Methods for Interface Agents that Learn , 1997, IEEE Trans. Knowl. Data Eng..

[128]  Yuichiro Anzai,et al.  LEMMING: A learning system for multi-robot environments , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[129]  B. Grosof.  Connict Resolution in Advice Taking and Instruction for Learning Agents 1 Challenges 1.1 Assimilation with Prior Knowledge 1.2 Importance of Yes/no Rules and Facts as Knowledge Representation , 2007 .

[130]  Theresa K. Lant,et al.  Computer simulations of organizations as experiential learning systems: implications for organization theory , 1994 .

[131]  J. March,et al.  Learning from Samples of One or Fewer , 1991 .

[132]  Maja J. Matarić,et al.  Leaning to behave socially , 1994 .

[133]  David Dery,et al.  Decision-making, problem-solving and organizational learning , 1983 .

[134]  V. Pucik,et al.  Strategic alliances, organizational learning, and competitive advantage: The HRM agenda , 1988 .

[135]  Edwin Hutchins,et al.  Organizing Work by Adaptation , 1991 .

[136]  J. Burgoyne,et al.  Towards the Learning Company , 1989 .

[137]  Arun Sharma,et al.  Finite Identification of Functions by Teams with Success Ratio 1\over2 and Above , 1995, Inf. Comput..

[138]  Salvatore J. Stolfo,et al.  Experiments on multistrategy learning by meta-learning , 1993, CIKM '93.