Learning Actions and Action Verbs from Human-Agent Interaction
نویسنده
چکیده
The goal of my research is to design agents that learn from human-agent interaction. Specifically, I am interested in acquisition of procedural, conceptual and linguistic knowledge related to novel actions from humanagent collaborative task execution.
منابع مشابه
An analytical on the gap between theory and action in Allamah Tabatabaei
The gap between theory and ethical action is known an important problem in ethics and education. Analyzing the relationship between theory and ethical action and deciding the elements having to do with optional actions of human and their interaction, one may perceive the reasons and roots of the gap and, on this basis, improve educational theories to attain the harmony between theory and action...
متن کاملA Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کاملMapping a corpus-induced ontology of action verbs on ItalWordNet
Action verbs are the least predictable linguistic type for bilingual dictionaries and they cause major problems for NLP technologies. This is not only because of language specific phraseology, but it is rather a consequence of the peculiar way each language categorizes events. In ordinary languages the most frequent action verbs are “general”, since they extend productively to actions belonging...
متن کاملUtilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملDifferential effects of age-of-acquisition for concrete nouns and action verbs: evidence for partly distinct representations?
There is growing evidence that words that are acquired early in life are processed faster and more accurately than words acquired later, even by adults. As neuropsychological and neuroimaging studies have implicated different brain networks in the processing of action verbs and concrete nouns, the present study was aimed at contrasting reaction times to early and later-acquired action verbs and...
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 2012