Learning and decision: making for intention reconciliation

Rational, autonomous agents must be able to revise their commitments in the light of new opportunities. They must decide when to default on commitments to the group in order to commit to potentially more valuable outside offers. The SPIRE experimental system allows the study of intention reconciliation in team contexts. This paper presents a new framework for SPIRE that allows for mathematical specification and provides a basis for the study of learning. Analysis shows that a reactive policy can be expected to perform as well as more complex policies that look ahead. We present an algorithm for learning when to default on group commitments based solely on observed values of group-related tasks and discuss the applicability of this algorithm in settings where multiple agents may be learning.

[1]  Michael E. Bratman,et al.  Intention, Plans, and Practical Reason , 1991 .

[2]  Sarit Kraus,et al.  The influence of social norms and social consciousness on intention reconciliation , 2002, Artif. Intell..

[3]  Alyssa Glass.  Creating Socially Conscious Agents: Decision-Making in the Context of Group Commitments , 1999 .

[4]  Barbara J. Grosz,et al.  Socially Conscious Decision-Making , 2000, AGENTS '00.

[5]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[6]  Sarit Kraus,et al.  Intention Reconcilation in the Context of Teamwork: An Initial Empirical Investigation , 1999, CIA.

[7]  L. Shapley,et al.  Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.

[8]  Victor R. Lesser,et al.  Advantages of a Leveled Commitment Contracting Protocol , 1996, AAAI/IAAI, Vol. 1.

[9]  Liz Sonenberg,et al.  Investigating Commitment Flexibility in Multi-Agent Contracts , 2002 .

[10]  Manuela Veloso,et al.  An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning , 2000 .

[11]  O. J. Vrieze,et al.  Stochastic Games with Finite State and Action Spaces. , 1988 .

[12]  Sandip Sen,et al.  Effects of misconception on reciprocative agents , 1998, AGENTS '98.

[13]  Craig Boutilier,et al.  The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems , 1998, AAAI/IAAI.

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

[15]  Sarit Kraus,et al.  Intention reconciliation by collaborative agents , 2000, Proceedings Fourth International Conference on MultiAgent Systems.