Login / Signup
Almost sure optimality and optimality in probabilityfor stochastic control problems over aninfinite time horizon.
Paolo Dai Pra
Giovanni B. Di Masi
Barbara Trivellato
Published in:
Ann. Oper. Res. (1999)
Keyphrases
</>
control problems
reinforcement learning
optimal control
optimal solution
adaptive control
average reward
queueing systems
state space
stochastic model
average cost
stochastic control