✳flâneur — a map of the web's best reading

Learning Latent Plans from Play

learning-from-play.github.io · 7,954 words · saved by 1 readers

We propose learning from teleoperated play data as a way to scale up multi-task robotic skill learning. Learning from play (LfP) offers three main advantages: 1) It is cheap. Large amounts of play data can be collected quickly as it does not require scene staging, task segmenting, or resetting to an initial state. 2) It is general. It contains both functional and non-functional behavior, relaxing the need for a predefined task distribution. 3) It is rich. Play involves repeated, varied behavior and naturally leads to high coverage of the possible interaction space. These properties distinguish play from expert demonstrations, which are rich, but expensive, and scripted unattended data collection, which is cheap, but insufficiently rich. Variety in play, however, presents a multimodality challenge to methods seeking to learn control on top. To this end, we introduce Play-LMP, a method designed to handle variability in the LfP setting by organizing it in an embedding space. Play-LMP join

Learning Latent Plans from Play Learning Latent Plans from Play scroll down Learning Latent Plans from Play Corey Lynch Google Brain Mohi Khansari Google X Ted Xiao Google Brain Vikash Kumar Google Brain Jonathan Tompson Google Brain Sergey Levine Google Brain Pierre Sermanet Google Brain March 5 2019 Download PDF Abstract We propose learning from teleoperated play data as a way to scale up multi-task robotic skill learning. Learning from play (LfP) offers three main advantages: 1) It is cheap . Large amounts of play data can be collected quickly as it does not require scene staging, task segm

Explore this link on the map →

saved by

related reading