Adaptability Preserving Domain Decomposition for Stabilizing Sim2Real Reinforcement Learning.

Haichuan Gao Zhile Yang Xin Su Tian Tan Feng Chen

Published in: IROS (2020)

Keyphrases

reinforcement learning
domain specific
function approximation
real life
state space
temporal difference
dynamic programming
machine learning
markov decision processes
transfer learning
denoising
cross domain
domain independent
domain experts
multi agent
multiscale
learning algorithm