SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning.

Marco Bagatella Sammy Joe Christen Otmar Hilliges

Published in: Trans. Mach. Learn. Res. (2022)

Keyphrases

reinforcement learning
state space
function approximation
learning algorithm
prior knowledge
machine learning
information systems
search algorithm
bayesian framework
temporal difference
transition model
exploration strategy
active exploration