pith. sign in

Seohong Park, Kevin Frans, Sergey Levine, and Aviral Kumar

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

3 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 3

roles

background 1

polarities

support 1

clear filters

representative citing papers

EXPO: Stable Reinforcement Learning with Expressive Policies

cs.LG · 2025-07-10 · conditional · novelty 7.0

EXPO stabilizes online RL for expressive policies by training a base policy with imitation and using a lightweight Gaussian edit policy to select higher-value actions on the fly for sampling and TD backups.

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

cs.LG · 2026-05-04 · unverdicted · novelty 6.0

OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • OGPO: Sample Efficient Full-Finetuning of Generative Control Policies cs.LG · 2026-05-04 · unverdicted · none · ref 78

    OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.