rl-at-scale.github.io - Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

home > domains > rl-at-scale.github.io

Description: Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

Example domain paragraphs

We describe a system for deep reinforcement learning of robotic manipulation skills applied to a large-scale real-world task: sorting recyclables and trash in office buildings. Real-world deployment of deep RL policies requires not only effective training algorithms, but the ability to bootstrap real-world training and enable broad generalization. To this end, our system - RL at Scale (RLS) - combines scalable deep RL from real-world data with bootstrapping from training in simulation, and incorporates auxi

Bootstrapping

Once we have an initial sim2real policy and data collected using scripts in the real world, we are off to collecting data autonomously in a lab setting which we call a "robot classroom". While real-world office buildings can provide the most representative experience, the throughput in terms of data collection is limited – some days there will be a lot of trash to sort, some days not so much. Our robots collect a large portion of their experience in “robot classrooms.” In the classroom shown below, 20 robot

Links to rl-at-scale.github.io (4)

• tedxiao.me Ted Xiao - Google DeepMind
• yunfei-bai.com Home | Yunfei Bai
• kuanghuei.github.io Kuang-Huei Lee | Personal Website
• txizzle.github.io Ted Xiao - Google DeepMind