Confident Least Square Value Iteration with Local Access to a Simulator.

Botao Hao Nevena Lazic Dong Yin Yasin Abbasi-Yadkori Csaba Szepesvári

Published in: AISTATS (2022)

Keyphrases

least squares
markov decision processes
heuristic search
dynamic programming
optical flow
state space
simulation model
simulation platform
databases
remote access
belief space
policy iteration
high confidence
test bed
optimal policy
information systems
search engine