What Is Wrong With Us? Improving Robustness Through Social Diagnosis

Robust behavior in complex, dynamic environments mandates that intelligent agents autonomously monitor their own run-time behavior, detect and diagnose failures, and attempt recovery. This challenge is intensified in multiagent settings, where the coordinated and competitive behaviors of other agents affect an agent's own performance. Previous approaches to this problem have often focused on single agent domains and have failed to address or exploit key facets of multi-agent domains, such as handling team failures. We present SAM, a complementary approach to monitoring and diagnosis for multi-agent domains that is particularly well-suited for collaborative settings. SAM includes the following key novel concepts: First, SAM's failure detection technique, inspired by social psychology, utilizes other agents as information sources and detects failures both in an agent and in its teammates. Second, SAM performs social diagnosis, reasoning about the failures in its team using an explicit model of teamwork (previously, teamwork models have been employed only in prescribing agent behaviors in teamwork). Third, SAM employs model sharing to alleviate the inherent inefficiencies associated with representing multiple agent models. We have implemented SAM in a complex, realistic multi-agent domain, and provide detailed empirical results assessing its benefits.

[1]  Pamela J. Fink,et al.  If at first you don't succeed , 2000, Nature Immunology.

[2]  Peter Bakker,et al.  Robot see, robot do: An overview of robot imitation , 1996 .

[3]  Milind Tambe,et al.  Intelligent Agents for Interactive Simulation Environments , 1995, AI Mag..

[4]  P. Pandurang Nayak,et al.  A Model-Based Approach to Reactive Self-Configuring Systems , 1996, AAAI/IAAI, Vol. 2.

[5]  Hector J. Levesque,et al.  On Acting Together , 1990, AAAI.

[6]  Joseph Y. Halpern,et al.  Knowledge and common knowledge in a distributed environment , 1984, JACM.

[7]  Edmund H. Durfee,et al.  Expecting the Unexpected: Detecting and Reacting to Unplanned-for World States , 1996, AAAI/IAAI, Vol. 2.

[8]  Nicholas R. Jennings,et al.  Controlling Cooperative Problem Solving in Industrial Multi-Agent Systems Using Joint Intentions , 1995, Artif. Intell..

[9]  David Atkinson,et al.  Generating Perception Requests and Expectations to Verify the Execution of Plans , 1986, AAAI.

[10]  Edmund H. Durfee,et al.  An Initial Assessment of Plan-Recognition-Based Coordination for Multi-Agent Teams , 1996 .

[11]  Milind Tambe,et al.  Tracking Dynamic Team Activity , 1996, AAAI/IAAI, Vol. 1.

[12]  L. Festinger A Theory of Social Comparison Processes , 1954 .

[13]  R. James Firby,et al.  An Investigation into Reactive Planning in Complex Domains , 1987, AAAI.

[14]  Hiroaki Kitano,et al.  RoboCup: The Robot World Cup Initiative , 1997, AGENTS '97.

[15]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[16]  Milind Tambe,et al.  Towards Flexible Teamwork , 1997, J. Artif. Intell. Res..

[17]  Richard Reviewer-Granger Unified Theories of Cognition , 1991, Journal of Cognitive Neuroscience.