Authors:
Oussama H. Hamid
1
and
Jochen Braun
2
Affiliations:
1
University of Kurdistan Hewlêr, Iraq
;
2
Otto-von-Guericke University, Germany
Keyword(s):
Attractor Neural Networks, Model-Based and Model-Free Reinforcement Learning, Stability-Plasticity Dilemma, Multiple Brain Systems, Temporal Statistics.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Fuzzy Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Learning Paradigms and Algorithms
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Reinforcement Learning
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Soft Computing and Intelligent Agents
;
Theory and Methods
Abstract:
It is widely accepted that reinforcement learning (RL) mechanisms are optimal only if there is a predefined
set of distinct states that are predictive of reward. This poses a cognitive challenge as to which events or
combinations of events could potentially predict reward in a non-stationary environment. In addition, the
computational discrepancy between two families of RL algorithms, model-free and model-based RL, creates
a stability-plasticity dilemma, which in the case of interactive and competitive multiple brain systems poses
a question of how to guide optimal decision-making control when there is competition between two systems
implementing different types of RL methods. We argue that both computational and cognitive challenges can
be met by infusing the RL framework as an algorithmic theory of human behavior with the strengths of the
attractor framework at the level of neural implementation. Our position is supported by the hypothesis that
‘attractor states’ which are
stable patterns of self-sustained and reverberating brain activity, are a manifestation
of the collective dynamics of neuronal populations in the brain. Hence, when neuronal activity is described at
an appropriate level of abstraction, simulations of spiking neuronal populations capture the collective dynamics
of the network in response to recurrent interactions between these populations.
(More)