TEMPERA: Test-Time Prompting via Reinforcement Learning.

Tianjun Zhang Xuezhi Wang Denny Zhou Dale Schuurmans Joseph E. Gonzalez

Published in: CoRR (2022)

Keyphrases

reinforcement learning
real time
computer vision
stochastic approximation
website
test cases
markov decision processes
autonomous learning
database
markov decision process
reward function
function approximation
state space
dynamic programming
case study
feature selection
genetic algorithm