Army research leads to more effective training model for robots
E-Mail IMAGE: New Army research reduces the unpredictability of current training reinforcement learning policies so that they are more practically applicable to physical systems, especially ground robots. These learning components will permit... view more Credit: (Photo illustration / U.S. Army) ADELPHI, Md. -- Multi-domain operations, the Army's future operating concept, requires autonomous agents with learning components to operate alongside the warfighter. New Army research reduces the unpredictability of current training reinforcement learning policies so that they are more pr...
Source: eurekalert.org