Model based planners reflect on their model-free propensities.

Rani Moran Mehdi Keramati Raymond J. Dolan

Published in: PLoS Comput. Biol. (2021)

Keyphrases

model free
reinforcement learning
function approximation
reinforcement learning algorithms
temporal difference
policy iteration
policy evaluation
dynamic programming
average reward
learning algorithm
pattern recognition
sufficient conditions
heuristic search
planning problems
impedance control