Non-blocking Asynchronous Training for Reinforcement Learning in Real-World Environments.

Peter Böhm Pauline Pounds Archie C. Chapman

Published in: IROS (2022)

Keyphrases

reinforcement learning
supervised learning
training set
training process
markov decision processes
state space
function approximation
training phase
reinforcement learning algorithms
real time
neural network
machine learning
learning algorithm
training examples
transfer learning
robot control