Hierarchical Common-Sense Interaction Learning
نویسندگان
چکیده
We describe a hierarchical learning approach for effective coordination in repeated games based on a commonsense decomposition of the “coordination problem”. In contrast to most other research on mechanism design and game-learning, we concentrate on breaking down the top-level problem into simpler learning tasks concerned with learning (i) utility functions, (ii) best-response strategies and (iii) cooperation potentials. We also report on empirical results with the layered learning architecture LAYLA that is constructed using these sub-components in a resource-load balancing scenario. The positive results show that the approach deserves further investigation, although a number of (possibly problem-inherent) difficulties illustrate the limitations of learning approaches in realworld applications.
منابع مشابه
The Role of Self-Directed Learning Readiness and Critical Thinking Disposition in Students’ Interaction in Blended Learning Environment
Introduction: Since electronic interaction of students in teaching-learning process in blended learning as well as identification of factors influencing it are essential, this study aimed to investigate the role of self-directed learning readiness and critical thinking disposition in Nursing and Midwifery students’ interaction in blended learning environment. Methods: This descriptive study was...
متن کاملHierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge
We present a learning architecture for lexical semantic classification problems that supplements task-specific training data with background data encoding general “world knowledge”. The model compiles knowledge contained in a dictionaryontology into additional training data, and integrates task-specific and background data through a novel hierarchical learning architecture. Experiments on a wor...
متن کاملEliciting collaborative social interactions via online games
The vision in Human Robot Interaction is that autonomous robots will have the ability to understand common sense behavioral patterns. We present a method of learning these behavior patterns through a multi-modal online game where two players collaborate to create a salad through selecting and discussing available salad items. Our approach relies heavily on the creation of a virtual environment ...
متن کاملA Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge
Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valuable resource for NLP applications. We present a hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities. Events and constraints on event ordering are induced jointly in one unified framework. We use a statistical mode...
متن کاملUnsupervised learning of common sense event structures from simple English stories
We present a program that builds up an internal event representation by exposure to common sense stories. The stories come from the OMICS corpus, and are English narratives about the steps involved with everyday household tasks, such as “get the mail” and “make a bed”. With repeated exposure to different stories describing the same events, our program learns a sequential hierarchical structure ...
متن کامل