Open Access
Interactive Task Learning for Simple Games
James R. Kirk,John E. Laird +1 more
- 01 Jan 2014
Vol. 3, pp 13-30
TL;DR: The structure and functionality of Rosie is described, and its competence, generality, communication efficiency, communication accessibility, and ability to continuously learn and accumulate new tasks and new task knowledge are evaluated.
read more
Abstract: We present an agent, called RosieTAG, that 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 task knowledge.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
40 years of cognitive architectures: core cognitive abilities and practical applications
Iuliia Kotseruba,John K. Tsotsos +1 more
TL;DR: This survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.
Cognitive Architectures for Language Agents
Theodore R. Sumers,Shunyu Yao,Karthik Narasimhan,Thomas L. Griffiths +3 more
TL;DR: CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions.
Interactive Task Learning
John E. Laird,Kevin A. Gluck,John R. Anderson,Kenneth D. Forbus,Odest Chadwicke Jenkins,Christian Lebiere,Dario D. Salvucci,Matthias Scheutz,Andrea L. Thomaz,Greg Trafton,Robert E. Wray,Shiwali Mohan,James R. Kirk +12 more
TL;DR: This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how to perform a task better but the actual definition of a task through natural interaction with a human instructor while attempting to perform the task.
•Posted Content
A Review of 40 Years of Cognitive Architecture Research: Core Cognitive Abilities and Practical Applications
Iuliia Kotseruba,John K. Tsotsos +1 more
TL;DR: A broad overview of the last 40 years of research on cognitive architectures, describing a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.
65
Spoken Instruction-Based One-Shot Object and Action Learning in a Cognitive Robotic Architecture
Matthias Scheutz,Evan Krause,Brad Oosterveld,Tyler M. Frasca,Robert W. Platt +4 more
- 08 May 2017
TL;DR: This work provides the first demonstration of spoken instruction-based one-shot object and action learning in a cognitive robotic architecture and discusses the modifications to several architectural components required to enable such fast learning.
54
References
Some studies in machine learning using the game of checkers
TL;DR: In this article, two machine learning procedures have been investigated in some detail using the game of checkers, and enough work has been done to verify the fact that a computer can be programmed so that it will lear...
Some studies in machine learning using the game of checkers
Arthur L. Samuel
- 31 Oct 1995
TL;DR: In this article, it was shown that a computer can learn to play a better game of checkers than can be played by the person who wrote the program, in a remarkably short period of time (8 or 10 hours of machine-playing time) when given only the rules of the game, a sense of direction, and a redundant and incomplete list of parameters which are thought to have something to do with the game.
2.8K
•Book
How Can the Human Mind Occur in the Physical Universe
John R. Anderson
- 17 Aug 2007
TL;DR: This chapter discusses cognitive architecture, which describes the architecture of the mind and the role that language plays in the development of thought.
1.5K
Some studies in machine learning using the game of checkers
TL;DR: Enough work has been done to verify the fact that a computer can be programmed so that it will learn to play a better game of checkers than can be played by the person who wrote the program.
•Book
The Soar Cognitive Architecture
John E. Laird
- 13 Apr 2012
TL;DR: This book offers the definitive presentation of Soar from theoretical and practical perspectives, providing comprehensive descriptions of fundamental aspects and new components, and proposes requirements for general cognitive architectures and explicitly evaluates how well Soar meets those requirements.
1K
Related Papers (5)
John E. Laird
- 13 Apr 2012
Łukasz Kaiser
- 22 Jul 2012
James R. Kirk,Aaron Mininger,John E. Laird +2 more
- 01 Oct 2016