Adapting Control Policies from Simulation to Reality Using a Pairwise Loss.

Ulrich Viereck Xingchao Peng Kate Saenko Robert Platt Jr.

Published in: ISER (2018)

Keyphrases

control policies
pairwise
reinforcement learning
stochastic optimization problems
control policy
motion control
markov random field
optimal policy
control system
higher order
neural network
experimental data
dynamic systems
finite horizon