TY - RPRT TI - Simultaneous Policy and Discrete Communication Learning for Multi-Agent Cooperation AU - Freed, Benjamin AU - Sartoretti, Guillaume (ORCID:0000000275799916) AU - Choset, Howie (ORCID:0000000254347945) PY - 2020 DO - 10.1109/lra.2020.2972862 UR - https://www.osti.gov/biblio/1799565 ID - 1799565 ER -