DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety.

André Correia Luís A. Alexandre

Published in: ESANN (2023)

Keyphrases

dynamic time warping
reinforcement learning
game theory
model free
game theoretic
state space
event sequences
filtering method
optimal policy
markov decision processes
function approximation
learning agents
filtering algorithm
countermeasures
information filtering
distance measure
denoising
learning process