New adversarial-arrival principal-agent model with regret upper bounds for greedy and smooth agents, but the claimed matching lower bound for the smooth setting is invalid because the constructed instance is not L-Lipschitz.
Principal-agent reward shaping in mdps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
New adversarial-arrival principal-agent model with regret upper bounds for greedy and smooth agents, but the claimed matching lower bound for the smooth setting is invalid because the constructed instance is not L-Lipschitz.