Login / Signup
Convergence of the Relative Value Iteration for the Ergodic Control Problem of Nondegenerate Diffusions under Near-Monotone Costs.
Ari Arapostathis
Vivek S. Borkar
K. Suresh Kumar
Published in:
SIAM J. Control. Optim. (2014)
Keyphrases
</>
upper bound
human errors
lower bound
state space
markov chain
convergence rate
convergence speed
multiscale
reinforcement learning
search space
heuristic search
variational inequalities
stationary distribution
iterative algorithms
stochastic shortest path