Controlling Underestimation Bias in Reinforcement Learning via Quasi-median Operation.

Wei Wei Yujia Zhang Jiye Liang Lin Li Yyuze Li

Published in: AAAI (2022)

Keyphrases

reinforcement learning
function approximation
optimal policy
reinforcement learning algorithms
temporal difference
supervised learning

state space
model free
multi agent
learning process
control system

neural network
decision trees
transfer learning
markov decision processes
learning problems

evaluation function
learning algorithm
information retrieval
machine learning
real world