Confidence-Conditioned Value Functions for Offline Reinforcement Learning.

Joey Hong Aviral Kumar Sergey Levine

Published in: ICLR (2023)

Keyphrases

reinforcement learning
high confidence
real time
function approximation
machine learning
temporal difference
database
learning algorithm
decision trees
confidence measure
action selection
optimal policy
sufficient conditions
supervised learning
state space
multi agent systems
multi agent
multiscale
data sets