TEMPERA: Test-Time Prompt Editing via Reinforcement Learning.

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

Published in: ICLR (2023)

Keyphrases

reinforcement learning
test cases
test data
function approximation
databases
state space
statistical tests
statistical significance
robotic control
data sets
least squares
optimal policy
software testing
temporal difference learning