Learning Real-World Robot Policies by Dreaming

05/20/2018
by   AJ Piergiovanni, et al.
0

Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of samples to learn a policy which can take significant time. In this paper, we focus on the problem of learning real-world robot action policies solely based on a few random off-policy samples. We learn a realistic dreaming model that can emulate samples equivalent to a sequence of images from the actual environment, and make the agent learn action policies by interacting with the dreaming model rather than the real world. We experimentally confirm that our dreaming model can learn realistic policies that transfer to the real-world.

READ FULL TEXT

page 5

page 6

page 8

page 12

research
03/24/2020

Learning to Play Soccer by Reinforcement and Applying Sim-to-Real to Compete in the Real World

This work presents an application of Reinforcement Learning (RL) for the...
research
10/11/2016

Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model

Developing control policies in simulation is often more practical and sa...
research
10/08/2019

Model-based Behavioral Cloning with Future Image Similarity Learning

We present a visual imitation learning framework that enables learning o...
research
06/04/2019

Off-Policy Evaluation via Off-Policy Classification

In this work, we consider the problem of model selection for deep reinfo...
research
03/08/2023

Learning Exploration Strategies to Solve Real-World Marble Runs

Tasks involving locally unstable or discontinuous dynamics (such as bifu...
research
10/26/2017

DoShiCo: a Domain Shift Challenge for Control

Training deep neural control networks end-to-end for real-world applicat...
research
07/04/2021

Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces

Autonomous robots require high degrees of cognitive and motoric intellig...

Please sign up or login with your details

Forgot password? Click here to reset