Interactions between supervised and reinforcement learning processes in a neurorobotic model
Capirchio, A.; Ponte, C.; Baldassarre, G.; Mannella, F.; Pelosin, E.; Caligiore, D.
Show abstract
Several influential works propose that the acquisition of motor behavior involves different learning mechanisms in the brain, in particular supervised and reinforcement learning, that are respectively associated with cerebellar-thalamocortical and basal ganglia-thalamocortical networks. Despite increasing evidence suggesting anatomical and functional interactions between these circuits, the learning processes operating within them are studied in isolation, neglecting their strong interdependence. This article proposes a bio-inspired neurorobotic model implementing a possible cooperation mechanism between supervised and reinforcement learning. The model, validated with empirical data from healthy participants and patients with cerebellar ataxia, shows how the integration of the two learning processes could lead to benefit both learning performance and movement accuracy.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The spinal cord facilitates cerebellar upper limb motor learning and control; inputs from neuromusculoskeletal simulation 97%
- An approximate stochastic optimal control framework to simulate nonlinear neuromusculoskeletal models in the presence of noise 96%
- Co-Contraction Embodies Uncertainty: An Optimal Feedforward Strategy for Robust Motor Control 96%
Similar papers in this journal
- Collective Evolution Learning Model for Vision-Based Collective Motion with Collision Avoidance 94%
- Biological data questions the support of the self inhibition required for pattern generation in the half center model. 94%
- A Hessian-based decomposition characterizes how performance in complex motor skills depends on individual strategy and variability 94%
Similar papers in this journal
- Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation 95%
- A model of the cerebellum generates gait adaptations in a reflex-based neuromusculoskeletal model during split-belt walking 95%
- Towards AI-based Precision Rehabilitation via Contextual Model-based Reinforcement Learning 92%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.