An intrinsically-motivated schema mechanism to model and simulate emergent cognition

@article{Georgeon2012AnIS,
  title={An intrinsically-motivated schema mechanism to model and simulate emergent cognition},
  author={Olivier L. Georgeon and Frank E. Ritter},
  journal={Cognitive Systems Research},
  year={2012},
  volume={15},
  pages={73-92}
}
Demonstrating sensemaking emergence in artificial agents: A method and an example
TLDR
It is argued that the agent's behavior demonstrates sensemaking if the agent learns to exploit regularities of interaction to fulfill its self-motivation as if it understood (at least partially) the underlying functioning of the environment.
A Constructivist Approach and Tool for Autonomous Agent Bottom-up Sequential Learning
TLDR
This work proposes the Bottom-up hiErarchical sequential Learning algorithm with Constructivist pAradigm (BEL-CA) to design agents capable of learning autonomously and continuously through interactions and proposes a toolkit to analyze the learning process at run time called GAIT.
Designing environment-agnostic agents
We present autonomous agents that are designed without encoding strategies or knowledge of the environment in the agent. The design approach focuses on the notion of sensorimotor patterns of
Exploration of the Functional Properties of Interaction: Computer Models and Pointers for Theory
TLDR
This work describes computational models inspired from swarm intelligence that may serve as the basis for complex operations, yielding the elaboration of knowledge and goal-directed behavior in the context of the interaction between the organism and the environment.
Artificial Interactionism: Avoiding Isolating Perception From Cognition in AI
TLDR
It is argued that such a renouncement opens interesting ways to explore the possibilities for designing artificial agents with intrinsic motivations and constitutive autonomy as well as drawing on the inversion of the interaction cycle.
Inferring Actions and Observations from Interactions
This study follows the Radial Interactionism (RI) cognitive modeling paradigm introduced previously by Georgeon and Aha (2013). An RI cognitive model uses sensorimotor interactions as
Interactional Motivation in artificial systems: Between extrinsic and intrinsic motivation
TLDR
A formal definition of the IM paradigm is introduced and it is argued that IM is a form of self-motivation on the same level as intrinsic motivation.
...
...

References

SHOWING 1-10 OF 105 REFERENCES
Intrinsic Motivation Systems for Autonomous Mental Development
TLDR
The mechanism of Intelligent Adaptive Curiosity is presented, an intrinsic motivation system which pushes a robot towards situations in which it maximizes its learning progress, thus permitting autonomous mental development.
A Model and Simulation of Early-Stage Vision as a Developmental Sensorimotor Process
TLDR
A model has been developed that coupled an intrinsically motivated schema mechanism with a visual system to connect vision with sequences and suggests new ways to implement vision and intrinsic motivation in artificial systems.
Interactionist-expectative view on agency and learning
Motivational Representations within a Computational Cognitive Architecture
  • R. Sun
  • Psychology
    Cognitive Computation
  • 2009
TLDR
This paper hypothesizes the need for implicit drive representations, as well as explicit goal representations, to make cognitive architectural models more comprehensive and provide deeper explanations of psychological processes.
The constructivist learning architecture: a model of cognitive development for robust autonomous robots
TLDR
This dissertation presents a model, the Constructivist Learning Architecture (CLA), that builds a hierarchical knowledge base using a set of interconnected self-organizing learning modules that can be used to better understand how people learn for their environment in infancy and adulthood.
Map Learning with Uninterpreted Sensors and Effectors
Six views of embodied cognition
TLDR
The sixth claim has received the least attention in the literature on embodied cognition, but it may in fact be the best documented and most powerful of the six claims.
A Hybrid Architecture for Situated Learning of Reactive Sequential Decision Making
TLDR
CLARION is a hybrid connectionist model consisting of both localist and distributed representations, based on the two-level approach proposed in [40], which unifies connectionist, reinforcement, and symbolic learning in a synergistic way, to perform on-line, bottom-up learning.
Constructivist Anticipatory Learning Mechanism ( CALM ) – dealing with partially deterministic and partially observable environments
This paper presents CALM (Constructivist Anticipatory Learning Mechanism), an agent learning mechanism based on a constructivist approach. It is designed to deal dynamically and interactively with
Made-up minds - a constructivist approach to artificial intelligence
TLDR
The schema mechanism is introduced, methodological underpinnings of constructivist AI are explained, directions for future work, evaluation and summary.
...
...