Delight-gated exploration spends actions only when expected improvement times surprisal exceeds a gate price, recovers Pandora's reservation rule, and shows weaker regret growth than Thompson sampling or epsilon-greedy across bandits and MDPs with transferable hyperparameters.
X-armed bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Delightful Exploration
Delight-gated exploration spends actions only when expected improvement times surprisal exceeds a gate price, recovers Pandora's reservation rule, and shows weaker regret growth than Thompson sampling or epsilon-greedy across bandits and MDPs with transferable hyperparameters.