pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Holder Policy Optimisation

cs.LG · 2026-05-12 · unverdicted · novelty 6.0 · 2 refs

HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.

citing papers explorer

Showing 2 of 2 citing papers.

  • Discrete Flow Matching for Offline-to-Online Reinforcement Learning cs.LG · 2026-05-12 · unverdicted · none · ref 57

    DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.

  • Holder Policy Optimisation cs.LG · 2026-05-12 · unverdicted · none · ref 35 · 2 links

    HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.