Versatile Control of Fluid-Directed Solid Objects Using Multi-Task Reinforcement Learning
DescriptionWe propose a new fluid control method combining meta reinforcement learning and multi task training, which realize a versatile fluid-directed solid objects controller that can quickly transfer between fluid simulators with different parameters to accomplish series of sub-tasks by encoding the simulation environment and task objectives
Event Type
Technical Papers
TimeTuesday, 6 December 202210:00am - 12:00pm KST
Registration Categories