Abstract
Research on resource-bounded agents has established that rational agents need to be able to revise their commitments in light of new opportunities. In the context of collaborative activities, rational agents must be able to reconcile their intentions to do team-related actions with other, conflicting intentions. The SPIRE experimental system allows the process of intention reconciliation in team contexts to be simulated and studied. Initial work with SPIRE examined the impact of environmental factors and agent utility functions on individual and group outcomes in the context of one set of social norms governing collaboration. This paper extends those results by further studying the effect of environmental factors and the agents' level of social consciousness and by comparing the impact of two different types of social norms on agent behavior and outcomes. The results show that the choice of social norms influences the accuracy of the agents' responses to varying environmental factors, as well as the effectiveness of social consciousness and other aspects of agents' utility functions. In experiments using heterogeneous groups of agents, both sets of norms were susceptible to the free-rider effect. However, the gains of the less responsible agents were minimal, suggesting that agent designers would have little incentive to design agents that deviate from the standard level of responsibility to the group.
Highlights
A number of applications have been proposed that require agents to work collaboratively to satisfy a shared goal [11, 17, 37, 41, inter alia]
We present the results of experiments designed to compare the two social-commitment policies and to further examine the impact of environmental factors and agent characteristics—including social consciousness—on individual and group outcomes
The experiments make the simplifying assumptions that all agents are capable of doing all tasks and that all agents are initially available at all times. (SPIRE can handle the more general situation in which agents have different capabilities and availabilities, but we have yet to investigate this type of scenario.) Figure 2 summarizes the settings used for most of the experiments; departures from these values are noted in each experiment’s description
Summary
A number of applications have been proposed that require agents to work collaboratively to satisfy a shared goal [11, 17, 37, 41, inter alia]. In the context of such collaborative activities, agents need to be able to revise their commitments and plans as new opportunities arise, handling situations in which intentions to do teamrelated actions conflict with other possible actions or plans. This paper focuses on the process of decision-making that agents perform when reconciling conflicting intentions in these group-activity contexts, and it examines the use of both external social norms (e.g., imposing penalties when agents fail to honor their team commitments) and internal measures of social consciousness (e.g., an agent’s own sense of its reputation as a responsible collaborator) to influence the agents’ decisions. If an agent has adopted an intention to do some action β and is given the opportunity to do another action γ that would in some way preclude its being able to do β, the agent must decide between doing β and doing γ. In the domain of automated systems administration (see [39]), it might be reasonable to allow an agent committed to performing a file-system backup to break that commitment (to default) so that it can assist with crash recovery on another system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
