Conservative and Reward-driven Behavior Selection in a Commonsense Reasoning Framework
نویسندگان
چکیده
Comirit is a framework for commonsense reasoning that combines simulation, logical deduction and passive machine learning. While a passive, observation-driven approach to learning is safe and highly conservative, it is limited to interaction only with those objects that it has previously observed. In this paper we describe a preliminary exploration of methods for extending Comirit to allow safe action selection in uncertain situations, and to allow reward-maximizing selection of behaviors.
منابع مشابه
Ethnomethodology and Conversational Analysis
In a speech community, people utilize their communicative competence which they have acquired from their society as part of their distinctive sociolinguistic identity. They negotiate and share meanings, because they have commonsense knowledge about the world, and have universal practical reasoning. Their commonsense knowledge is embodied in their language. Thus, not only does social life depend...
متن کاملIntegrated Commonsense Reasoning and Probabilistic Planning
Commonsense reasoning and probabilistic planning are two of the most important research areas in artificial intelligence. This paper focuses on Integrated commonsense Reasoning and probabilistic Planning (IRP) problems. On one hand, commonsense reasoning algorithms aim at drawing conclusions using structured knowledge that is typically provided in a declarative way. On the other hand, probabili...
متن کاملPlanning in a Commonsense framework
This paper presents ideas and some work already done for developing a system that is capable of planning within a commonsense framework. Given a goal and a situation, that is not completely described, the system is able to plan using commonsense reasoning rules about the eeects of actions, rules that are typically but not always true. The use of commonsense reasoning rules leads to the introduc...
متن کاملComirit: Commonsense Reasoning by Integrating Simulation and Logic
Rich computer simulations or quantitative models can enable an agent to realistically predict real-world behavior with precision and performance that is difficult to emulate in logical formalisms. Unfortunately, such simulations lack the deductive flexibility of techniques such as formal logics and so do not find natural application in the deductive machinery of commonsense or general purpose r...
متن کاملInformation Compression by Multiple Alignment, Unification and Search as a Framework for Human-Like Reasoning
This paper is an overview of the idea that several aspects of human-like reasoning may be understood in a framework of information compression by ‘multiple alignment’, ‘unification’ and ‘search’. These concepts will be described in outline together with a description of the SP61 computer model which is a partial realisation of the framework. A selection of examples are presented, illustrated wi...
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 2009