Sim2Real Transfer for Reinforcement Learning without Dynamics Randomization.

Manuel Kaspar Juan David Muñoz Osorio Jürgen Bock

Published in: IROS (2020)

Keyphrases

reinforcement learning
transfer learning
function approximation
learning algorithm
dynamic model
databases
neural network
learning process
dynamic programming
privacy preserving
markov decision processes
model free
state space
optimal policy
cellular automata
autonomous learning