A gradient-based framework tunes epsilon-greedy exploration schedules by minimizing Bayesian regret, matching or beating heuristics in batched recommendation benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Optimization of Epsilon-Greedy Exploration
A gradient-based framework tunes epsilon-greedy exploration schedules by minimizing Bayesian regret, matching or beating heuristics in batched recommendation benchmarks.