Modeling task allocation using a decision theoretic model

Mediation is the process of decomposing a task into subtasks, finding agents suitable for these subtasks and negotiating with agents to obtain commitments to execute these subtasks. This process involves several decisions to be made by a mediator including which tasks to mediate, when to interrupt the current task mediation to pursue a better task, etc. The main contribution of this work is integrating the different aspects of a mediator decision problem into one coherent and simple decision theoretic model. This model is then used to learn an optimal policy for a mediator. We propose a generalization of the original Semi-MDP (SMDP) model, which allows efficient representation of the mediator decision problem. Also the concurrent action model (CAM) is extended to allow better performing policies to be found. Experimental results are presented showing how our model outperforms the original SMDP and CAM models. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learn...

• Type: Conference
• Year: 2005
• Where: ATAL
• Authors: Sherief Abdallah, Victor R. Lesser
• Keywords: Artificial Intelligence, ATAL 2005, Decision Theoretic Model, Mediator Decision Problem