6 results
Ranked from CortexLab’s local platform index and published content.
01
model
→02Contextual Bandit
Chooses among actions using context while learning from immediate reward.
model
→03Q-Learning
An off-policy temporal-difference method that learns action values from reward transitions.
model
→04Multilayer Perceptron
A stack of learned affine transformations and nonlinearities that approximates complex functions.
model
→05Thompson Sampling
Samples action quality from posterior beliefs to balance exploration and exploitation.
model
→06Graph Neural Network
Learns node/edge representations by passing messages across graph neighborhoods.
model
→Logistic Regression
A probabilistic classification baseline that is transparent, fast and surprisingly competitive.