Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning.

Yichen Chen Mengdi Wang

Published in: CoRR (2016)

Keyphrases

primal dual
reinforcement learning
sample complexity
linear programming
learning algorithm
lower bound
approximation algorithms
generalization error
machine learning
special case
upper bound
learning experience
transfer learning
learning problems
semidefinite programming
interior point methods