Properties of a temporal difference reinforcement learning brain machine interface driven by a simulated motor cortex.
Aditya TarigoppulaNick RotellaJoseph T. FrancisPublished in: EMBC (2012)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- td learning
- human brain
- evaluation function
- reinforcement learning algorithms
- monte carlo
- temporal difference learning
- action selection
- model free
- step size
- function approximators
- cerebral cortex
- policy evaluation
- cortical surface
- temporal difference methods
- sensory inputs
- markov decision processes
- actor critic
- state space
- basal ganglia
- inverse reinforcement learning
- dynamic programming
- neural network
- policy iteration
- support vector machine svm
- supervised learning