Near-Optimal Learning and Planning in Separated Latent MDPs.

Fan Chen Constantinos Daskalakis Noah Golowich Alexander Rakhlin

Published in: CoRR (2024)

Keyphrases

reinforcement learning
learning systems
stochastic domains
markov decision processes
learning algorithm
partially observable
learning process
supervised learning
state space
linear programming
learning tasks
latent variables
decision theoretic
decision theoretic planning
macro actions