Learning Task Formulations through Situated Interactive Instruction
نویسندگان
چکیده
We present an agent, called RosieTAG, which is implemented in Soar and interacts with an external robotic environment. Rosie learns new games through interactive instruction with a human via restricted natural language. Instead of learning policy or strategy information as is common in other game learners, Rosie learns multiple game formulations (the objects, players, and rules of a game) and then uses its own general strategies to solve them. We describe the structure and functionality of Rosie, and evaluate its competence, generality, communication efficiency, communication accessibility, and ability to continuously learn and accumulate new tasks and new
منابع مشابه
A Computational Model for Situated Task Learning with Interactive Instruction
Learning novel tasks is a complex cognitive activity requiring the learner to acquire diverse declarative and procedural knowledge. Prior ACT-R models of acquiring task knowledge from instruction focused on learning procedural knowledge from declarative instructions encoded in semantic memory. In this paper, we identify the requirements for designing computational models that learn task knowled...
متن کاملTowards Situated, Interactive, Instructable Agents in a Cognitive Architecture
This paper discusses the challenge of designing instructable agents that can learn through interaction with a human expert. Learning through instruction is a powerful paradigm for acquiring knowledge because it limits the complexity of the learning task in a variety of ways. To support learning through instruction, the agent must be able to effectively communicate its lack of knowledge to the h...
متن کاملThe effect of task-based instruction on reading comprehension of Iranian EFL learners
Developing reading comprehension ability is an important aspect in acquisition of a language. The present study focused on improving reading comprehension ability through Task-based Instruction (TBI). TBI is a methodology that develops from a focus on classroom tasks. The participants of the study were 135 Iranian female students at different levels selected from high sc...
متن کاملLearning Grounded Language through Situated Interactive Instruction
We present an approach for learning grounded language from mixed-initiative human-robot interaction. Prior work on learning from human instruction has concentrated on acquisition of task-execution knowledge from domainspecific language. In this work, we demonstrate acquisition of linguistic, semantic, perceptual, and procedural knowledge from mixed-initiative, natural language dialog. Our appro...
متن کاملFlexibly Instructable Agents
This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a exible (and thus powerful) paradigm for teaching tasks because it allows an instructor to communicate whatever types of knowledge an agent might need in whatever situations might arise. To support this exibility, however, the agent must be able to learn ...
متن کامل