Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation.

Chenyang Zhao Timothy M. Hospedales

Published in: ACML (2021)

Keyphrases

reinforcement learning
peer to peer
transfer learning
domain specific
robotic control
data sets
parameter tuning
machine learning
mobile robot
dynamic programming
domain independent
watermarking scheme
robust estimation
temporal difference
learned knowledge
blocks world
neural network