Login / Signup
Approximate dynamic programming via sum of squares programming.
Tyler H. Summers
Konstantin Kunz
Nikolaos Kariotoglou
Maryam Kamgarpour
Sean Summers
John Lygeros
Published in:
ECC (2013)
Keyphrases
</>
approximate dynamic programming
linear program
dynamic programming
stochastic dynamic programming
reinforcement learning
programming language
factored mdps
step size
control policy
learning algorithm
optimal solution
search algorithm
least squares