Agents That Explain Their Own Actions
نویسنده
چکیده
Computer generated battleeeld agents need to be able to explain the rationales for their actions. Such explanations make it easier to validate agent behavior, and can enhance the eeectiveness of the agents as training devices. This paper describes an explanation capability called Debrief that enables agents implemented in Soar to describe and justify their decisions. Debrief determines the motivation for decisions by recalling the context in which decisions were made, and determining what factors were critical to those decisions. In the process Debrief learns to recognize similar situations where the same decision would be made for the same reasons. Debrief currently being used by the TacAir-Soar tactical air agent to explain its actions , and is being evaluated for incorporation into other reactive planning agents.
منابع مشابه
Agents that Learn to Explain Themselves
Intelligent artificial agents need to be able to explain and justify their actions. They must therefore understand the rationales for their own actions. This paper describes a technique for acquiring this understanding, implemented in a multimedia explanation system. The system determines the motivation for a decision by recalling the situation in which the decision was made, and replaying the ...
متن کاملLevi on Causal Decision Theory and the Possibility of Predicting One’s Own Actions
Isaac Levi has long criticized causal decision theory on the grounds that it requires deliberating agents to make predictions about their own actions. A rational agent cannot, he claims, see herself as free to choose an act while simultaneously making a prediction about her likelihood of performing it. Levi is wrong on both points. First, nothing in causal decision theory forces agents to make ...
متن کاملMany is More, But Not Too Many: Dimensions of Cooperation of Agents with and without Predictive Capabilities
This paper examines the tradeoffs between agents that can predict (and, therefore, take into account) other agent’s actions and agents that act on their own without taking other agents’ actions into account. A simple prediction mechanism allows agents to make reasonably accurate guesses about other agents’ future actions, thereby making better decisions about their own actions. Our experimental...
متن کاملMany is more: The utility of simple reactive agents with predictive mechanisms in multiagent object collection tasks
This paper examines the tradeoffs between agents that can predict (and, therefore, take into account) other agent’s actions and agents that act on their own without taking other agents’ actions into account. A simple prediction mechanism allows agents to make reasonably accurate guesses about other agents’ future actions, thereby making better decisions about their own actions. Our experimental...
متن کاملSelf-Explaining Agents in Virtual Training
Virtual training systems are increasingly used for the training of complex, dynamic tasks. To give trainees the opportunity to train autonomously, intelligent agents are used to generate the behavior of the virtual players in the training scenario. For effective training however, trainees should be supported in the reflection phase of the training as well. Therefore, we propose to use self-expl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1994