Skip to content. | Skip to navigation

Personal tools
Document Actions

Gianluca Baldassarre (2002)

A modular neural-network model of the basal ganglia's role in learning and selecting motor behaviours

Cognitive Systems Research, 3(2):5-13.

This work presents a modular neural-network model (based on reinforcement-learning actor-critic methods) that tries to capture some of the most relevant known aspects of the role that basal ganglia play in learning and selecting motor behavior related to different goals. The model uses a mixture of experts network for the critic and a hierarchical network with two levels for the actor. Some simulations with the model show that basal ganglia select ``chunks'' of behavior whose ``details'' are specified by direct sensory-motor pathways, and how emergent modularity can help to deal with tasks with asynchronous multiple goals. A ``top-down'' approach is adopted that first analyses some adaptive non-trivial interaction of a whole (simulated) organism with the environment, and its capacity to learn, and then attempts to implement these functions with neural architectures and mechanisms that have an empirical neuroanatomical and neurophysiological foundation.
Basal Ganglia; Dopamine; Modularity Neural Networks; Mixture of Experts Networks; Reinforcement Learning; Actor-Critic Methods; Multi-Goal Tasks
Relevant for: WP6 hierarchical architectures. One of the first proposals on an actor-critic RL hierarchical architecture based on mixture-of-experts networks. On this, see also: `Doya K., Samejima K., Katagiri K., Kawato M. (2002). Multiple model-based reinforcement learning.' which proposes a hierarchical RL architecture based on ideas drawn from mixtures-of-experts networks and the MOSAIC model.