A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays.

Huizhen Yu Yi Wan Richard S. Sutton

Published in: CoRR (2023)

Keyphrases

stochastic approximation
communication delays
control theory
monte carlo
precedence relations
execution times
np hard
processing times
multiprocessor systems
reinforcement learning
temporal difference learning
upper bound
linear programming