@article {pub4000,
	title = {Assessing Transferability from Simulation to Reality for Reinforcement Learning},
	author = {Fabio Muratore AND Michael Gienger AND Jan Peters},
	year = {2020},
	month = {June},
	abstract = {Learning  robot  control  policies  from  physics  simulations is of great interest for the robotics community as it mayrender the learning process faster, cheaper, and safer by alleviating the need for expensive real-world experiments. However, the direct transfer of the learned behavior from simulation to realityis  a  major  challenge.  Optimizing  a  policy  on  a  slightly  faulty simulator can easily lead to the maximization of the {\textquoteleft}SimulationOptimization  Bias{\textquoteright}  (SOB).  In  this  case,  the  optimizer  exploitsmodeling errors of the simulator such that the resulting behavior can  potentially  damage  the  robot.
We   tackle   this   challenge   by   applying   domain   randomization,  i.e.,  randomizing  the  parameters  of  the  physics  simulator  during  learning.  We  propose  an  algorithm  called Simulation-based  Policy  Optimization  with  Transferability  Assessment   (SPOTA)   which   uses   an   estimator   of   the   SOB   toformulate   a   stopping   criterion   for   training.   The   introduced estimator  quantifies  the  over-fitting  to  the  set  of  domains  experienced during training. Our experimental results in two different environments show that the new simulation-based policysearch algorithm is able to learn a control policy exclusively from a randomized  simulator,  which  can  be  applied  directly  to  real system  without  any  additional  training  on  the  latter.},
	publisher = {IEEE},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}
}