Signals 4 · free daily AI digest

Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport

Paper recorded by Signals 4 on 2026-09-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-14 on arXiv · recorded by Signals 4 on 2026-09-15

Category: cs.AI · 人工智能 · first seen 2026-09-15

Abstract

Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies can naturally represent such multimodal behaviors, but learning an efficient one-step flow policy remains challenging: standard value guidance often leads to mode collapse or exploits overestimation bias in out-of-distribution regions. To address this

Read on arXiv →

#70 most recent of 300 cs.AI papers we have recorded · ↑ newer: Privacy-enhanced federated learning via asynchronous aggregation and l · ↓ older: LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Di
Cite this page: Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport: the #70 most recent of 300 cs.AI papers we have recorded (as of 2026-09-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/learning-multimodal-one-step-flow-policy-via-value-weighted-optimal-transport.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions