Pith. sign in

Title resolution pending

The state value estimation function at iteration t is denoted as Vt(·) = Vθt(·) · 2018

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

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Divergence-Augmented Policy Optimization

cs.LG · 2025-01-25 · conditional · novelty 5.0

DAPO augments policy gradients with a multi-step KL divergence between the current and behavior policies, and reports better Atari scores in data-scarce off-policy training.

citing papers explorer

Showing 1 of 1 citing paper.

  • Divergence-Augmented Policy Optimization cs.LG · 2025-01-25 · conditional · none · ref 17

    DAPO augments policy gradients with a multi-step KL divergence between the current and behavior policies, and reports better Atari scores in data-scarce off-policy training.