Login / Signup
An actor critic algorithm based on Grassmanian search.
Prabuchandran K. J.
Shalabh Bhatnagar
Vivek S. Borkar
Published in:
CDC (2014)
Keyphrases
</>
search space
learning algorithm
optimal solution
dynamic programming
optimization algorithm
objective function
cost function
actor critic
mathematical model
convergence proof
neural network
policy iteration
path finding
monte carlo
markov chain
simulated annealing
reinforcement learning