Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation.

Dmitry Kalashnikov Alex Irpan Peter Pastor Julian Ibarz Alexander Herzog Eric Jang Deirdre Quillen Ethan Holly Mrinal Kalakrishnan Vincent Vanhoucke Sergey Levine

Published in: CoRL (2018)

Keyphrases

reinforcement learning
manipulation tasks
real time
function approximation
augmented reality
real robot
parallel robot
computer vision
state space

vision system
highly scalable
optimal policy
robotic systems
reinforcement learning algorithms
model free
perception action
temporal difference learning
mobile robot

markov decision processes
lightweight
dynamic programming
learning process
learning algorithm
robotic arm
imitation learning
deep learning
stochastic approximation

learning problems
robot control
web scale
robot navigation
multi agent
machine learning
neural network
data sets