Automatic Trade-off Adaptation in Offline RL.

Phillip Swazinna Steffen Udluft Thomas A. Runkler

Published in: ESANN (2023)

Keyphrases

trade off
reinforcement learning
semi automatic
learning process
fully automatic
neural network
multi agent
markov decision processes
function approximation
decision making
image sequences
state space
data driven
optimal policy
adaptation strategies