cd/entity/Critic-guided Relative Offline Policy optimization· home› entities› Critic-guided Relative Offline Policy optimization

grep -l @critic-guided relative offline policy optimization /news/*.json | wc -l → 1

Critic-guided Relative Offline Policy optimization

mentions 1 type Person feed RSS

// recent coverage 1 mentions

04:00

2026-09-21

machinebrief.com

machine-learning

OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios

Kuaishou deployed OneBid, a unified auto-bidding foundation model built on Decision Transformer, reporting an overall +2.2% ADVV gain on oCPX Ads and a peak +13.1% gain in the ROAS scenario in online …

// co-occurs with top 6 entities

OneBid 1 Kuaishou 1 Decision Transformer 1 Mixture-of-Experts 1 GRPO 1 oCPX 1

// topics top 3 topics

machine learning 1 ai research 1 artificial intelligence 1