Subtask-masked curriculum learning for reinforcement learning with application to UAV maneuver decision-making

Unmanned Aerial Vehicle (UAV) maneuver strategy learning remains a challenge when using Reinforcement Learning (RL) in this sparse reward task. In this paper, we propose Subtask-Masked curriculum learning for RL (SUBMAS-RL), an efficient RL paradigm that implements curriculum learning and knowledge transfer for UAV maneuver scenarios...

Abundant grain boundaries activate highly efficient lithium ion transportation in high rate Li₄Ti₅O₁₂ compact microspheres

It is a huge challenge for high-tap-density electrodes to achieve high volumetric energy density but without compromising the ionic transportation. Herein, we prepared compact Li₄Ti₅O₁₂ (LTO) microspheres consisting of densely packed primary nanoparticles. The real space distribution of lithium ions inside the...