TY - RPRT TI - Reinforcement learning in discrete action space applied to inverse defect design AU - Loeffler, Troy D. AU - Banik, Suvo AU - Patra, Tarak K. AU - Sternberg, Michael AU - Sankaranarayanan, Subramanian K. R. S. (ORCID:000000029708396X) PY - 2021 DO - 10.1088/2399-6528/abe591 UR - https://www.osti.gov/biblio/1835351 ID - 1835351 ER -