Elastic step DDPG: Multi-step reinforcement learning for improved sample efficiency.

Adrian Ly Richard Dazeley Peter Vamplew Francisco Cruz Sunil Aryal

Published in: IJCNN (2023)

Keyphrases

multi step
reinforcement learning
single step
lower bounding
k nearest neighbor
state space
knn
semi supervised
machine learning
tumor classification
function approximation
high dimensional
optimal policy
nearest neighbor
temporal difference
evolutionary algorithm
objective function
td learning
data sets