Mario Becomes Cognitive

Topics in Cognitive Science 9 (2):343-373 (2017)

Abstract
In line with Allen Newell's challenge to develop complete cognitive architectures, and motivated by a recent proposal for a unifying subsymbolic computational theory of cognition, we introduce the cognitive control architecture SEMLINCS. SEMLINCS models the development of an embodied cognitive agent that learns discrete production rule-like structures from its own, autonomously gathered, continuous sensorimotor experiences. Moreover, the agent uses the developing knowledge to plan and control environmental interactions in a versatile, goal-directed, and self-motivated manner. Thus, in contrast to several well-known symbolic cognitive architectures, SEMLINCS is not provided with production rules and the involved symbols, but it learns them. In this paper, the actual implementation of SEMLINCS causes learning and self-motivated, autonomous behavioral control of the game figure Mario in a clone of the computer game Super Mario Bros. Our evaluations highlight the successful development of behavioral versatility as well as the learning of suitable production rules and the involved symbols from sensorimotor experiences. Moreover, knowledge- and motivation-dependent individualizations of the agents’ behavioral tendencies are shown. Finally, interaction sequences can be planned on the sensorimotor-grounded production rule level. Current limitations directly point toward the need for several further enhancements, which may be integrated into SEMLINCS in the near future. Overall, SEMLINCS may be viewed as an architecture that allows the functional and computational modeling of embodied cognitive development, whereby the current main focus lies on the development of production rules from sensorimotor experiences.
Keywords Cognitive science and games  Language grounding  Cognitive architecture  Learning  Self‐motivated behavior  Artificial intelligence  Event schemata  Symbol grounding
Categories (categorize this paper)
DOI 10.1111/tops.12252
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

Our Archive


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 40,109
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

The Free-Energy Principle: A Rough Guide to the Brain?Karl Friston - 2009 - Trends in Cognitive Sciences 13 (7):293-301.
Computing Machinery and Intelligence.Alan M. Turing - 1950 - Mind 59 (October):433-60.

View all 16 references / Add more references

Citations of this work BETA

Games for Psychological Science.Andrew Howes - 2017 - Topics in Cognitive Science 9 (2):533-536.
Allen Newell's Program of Research: The Video‐Game Test.Fernand Gobet - 2017 - Topics in Cognitive Science 9 (2):522-532.

Add more citations

Similar books and articles

Sensorimotor Grounding and Reused Cognitive Domains.Maria Brincker - 2010 - Behavioral and Brain Sciences 33 (4):270--271.
Toward a Unified View of Cognitive Control.Dario D. Salvucci & Niels A. Taatgen - 2011 - Topics in Cognitive Science 3 (2):227-230.
The Newell Test for a Theory of Cognition.John R. Anderson & Christian Lebiere - 2003 - Behavioral and Brain Sciences 26 (5):587-601.

Analytics

Added to PP index
2017-02-08

Total views
19 ( #421,353 of 2,237,139 )

Recent downloads (6 months)
3 ( #595,368 of 2,237,139 )

How can I increase my downloads?

Downloads

My notes

Sign in to use this feature