Faster Policy Learning with Continuous-Time Gradients.

Samuel K. Ainsworth Kendall Lowrey John Thickstun Zaïd Harchaoui Siddhartha S. Srinivasa

Published in: CoRR (2020)

Keyphrases

learning process
learning algorithm
learning tasks
information systems
state space
learning systems
data sets
reinforcement learning
dynamic programming
probability distribution
learning problems
incremental learning
optimal control
inductive inference