Pith. sign in

Using confidence bounds for exploitation-exploration trade-offs.JournalofMachineLearningResearch, 3(Nov):397–422, 2002

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

First Return, Entropy-Eliciting Explore

cs.AI · 2025-07-09 · conditional · novelty 4.0

FR3E improves LLM math reasoning by finding high-entropy tokens in a trajectory and doing extra rollouts from those points to shape rewards.

citing papers explorer

Showing 1 of 1 citing paper.

  • First Return, Entropy-Eliciting Explore cs.AI · 2025-07-09 · conditional · none · ref 2

    FR3E improves LLM math reasoning by finding high-entropy tokens in a trajectory and doing extra rollouts from those points to shape rewards.