arXiv Machine Learning September 15, 2026 By Ziqi Zhao, Run Xu, Qingjian Ni

Learning Source Acquisition Policies by Offline Planning

Read the original on arXiv Machine Learning →

The paper introduces O-MPAC, an offline planning method for learning source acquisition policies under a limited budget. It transfers finite‑horizon risk‑cost targets from full training data into a shared source‑action scorer that re‑evaluates partial observations and source metadata after each query, applying a hard cost mask. Experiments show that O‑MPAC achieves high accuracy (0.965) in a routing task and outperforms several baselines on six real tasks, achieving the highest mean budget‑integrated accuracy on five of them.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

4d ago

Generative Support Realignment for Cross-Domain Offline Reinforcement Learning

arXiv:2605.13054v2 Announce Type: replace-cross Abstract: Cross-domain offline reinforcement learning learns a target policy from pre-collected source and target datasets with different dynamics. Whe...

By Minung Kim, Jeongmo Kim, Gwanwoo Choi, Seungyul Han

reinforcement-learning benchmarks

arXiv AI

Jul 14

Active Offline-to-Online Reinforcement Learning

arXiv:2607. 11720v1 Announce Type: cross Abstract: Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction.

By Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai

reinforcement-learning fine-tuning

Hugging Face Trending Papers

Jul 13

Active Offline-to-Online Reinforcement Learning

Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where interaction is costly or potentially hazardous.

reinforcement-learning fine-tuning

arXiv AI

Jul 28

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

arXiv:2607. 24720v1 Announce Type: cross Abstract: Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear.

By Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao

agents efficiency

arXiv AI

Sep 16

Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging

The paper introduces LP‑BTS, a learning‑guided planning framework for mobile charging in large, dynamic action spaces. It uses a graph proposal policy to narrow candidate stops, a value critic to evaluate leaf nodes, and edge‑budgeted PUCT to compare short simulated futures before action selection. Experiments on a 30‑scenario battery‑life benchmark show LP‑BTS achieving the highest survival and alive‑AUC, outperforming domain‑engineered baselines and heuristic policies.

By Liang-Ching Tao, Pi-Chung Wang

arXiv Machine Learning

Aug 4

BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition

arXiv:2608. 02305v1 Announce Type: new Abstract: Active feature acquisition (AFA) asks which unobserved feature to measure next for each test instance under a budget.

By Jiaorong Feng, Qian Li, Ying Li

benchmarks

One email a morning, machine-written

Related stories

Generative Support Realignment for Cross-Domain Offline Reinforcement Learning

Active Offline-to-Online Reinforcement Learning

Active Offline-to-Online Reinforcement Learning

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging

BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition