pith. machine review for the scientific record. sign in

Addressing function approximation error in actor-critic methods

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Learning to Reason under Off-Policy Guidance

cs.LG · 2025-04-21 · unverdicted · novelty 6.0

LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning to Reason under Off-Policy Guidance cs.LG · 2025-04-21 · unverdicted · none · ref 51

    LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.