Scholars Central

Conference abstractPublished 16 Apr 2018

A universal robotic control system using reinforcement learning with limited feedback

Authors: Michael Truell, Joshua Gruenstein

Horace Mann School, USA

Ask about this article

Abstract

Select any words in the title or abstract, or press this and choose a sentence.

A mobile robot deep reinforcement learning system is created that converges on common robotic tasks using four times less feedback than pre-existing solutions. The system achieves this leap in efficiency through context-aware action selection and aggressive online hyper-parameter optimization while still maintaining performance on embedded hardware. A core algorithm of deep wire fitted q-learning is supplemented with active measurement of robot uncertainty, defined as the derivative of error between expected and received reward. This uncertainty value directly scales the temperature of Boltzmann probabilistic exploration policy in addition to the learning rate of stochastic gradient descent. Furthermore, to provide generality across robots and tasks, neural network topology is efficiently evolved throughout training and evaluation. Finally, experience replay is extended to changing environments and is integrated with our uncertainty value. Human operators successfully trained the system on multiple robots in a matter of minutes to perform tasks such as driving to a point with a differential drive system, following a line using holonomic Swedish wheels or playing ping pong with a robot arm. All are without any manual hyperparameter adjustment in both simulation and hardware.

Ask about this article

Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.

Try:

Similar by topic

More from this journal

The newest in Advances in Robotics & Automation.

All its articles

Conferences in this field

Upcoming conferences in this field.

Follow

New articles from what you follow go into your email digest, once you agree to alert emails.

  • JournalAdvances in Robotics & Automation
  • SubjectComputer Science & IT
  • BylineArticles whose byline prints “Michael Truell”
  • BylineArticles whose byline prints “Joshua Gruenstein”

For authors and organisers

Publish, present and keep up with your field

Find the right journal for your paper and submit your manuscript.

Photo: Pexels