Sign in
Approximate dynamic programming via direct search in the space of value function approximations.
Edilson F. Arruda
Marcelo D. Fragoso
João Bosco Ribeiro do Val
Published in:
Eur. J. Oper. Res. (2011)
Keyphrases
</>
approximate dynamic programming
direct search
linear program
stationary points
control policy
step size
genetic algorithm
reinforcement learning
search space
differential evolution
hill climbing
dynamic programming
machine learning
graphical models