Login / Signup
Dynamic regret convergence analysis and an adaptive regularization algorithm for on-policy robot imitation learning.
Jonathan N. Lee
Michael Laskey
Ajay Kumar Tanwani
Anil Aswani
Ken Goldberg
Published in:
Int. J. Robotics Res. (2021)
Keyphrases
</>
convergence analysis
dynamic programming
optimal solution
learning algorithm
cost function
simulated annealing
global optimum
optimality conditions
worst case
vision system
particle swarm optimization
global convergence
genetic algorithm
lower bound
search space
imitation learning