Performance Analysis of Coherency Control Policies through Lock Retention.

Asit Dan Philip S. Yu

Published in: SIGMOD Conference (1992)

Keyphrases

control policies
reinforcement learning
optimal policy
stochastic optimization problems
control system
control policy
control strategies
finite horizon
action space
motion control
markov decision processes
long run
dynamic programming
state space
decision problems
infinite horizon
multi agent
neural network