Multi-Task Robotic Reinforcement Learning at Scale

Multi-Task Robotic Reinforcement Learning at Scale

Multi-Task Robotic Reinforcement Learning at Scale

“For general-purpose robots to be most useful, they would need to be able to perform a range of tasks, such as cleaning, maintenance and delivery. But training even a single task (e.g., grasping) using offline reinforcement learning (RL), a trial and error learning method where the agent uses training previously collected data, can take thousands of robot-hours, in addition to the significant engineering needed to enable autonomous operation of a large-scale robotic system. Thus, the computational costs of building general-purpose everyday robots using current robot learning methods becomes prohibitive as the number of tasks grows…”

Source: ai.googleblog.com/2021/04/multi-task-robotic-reinforcement.html