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.
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...
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.
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.
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.
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.
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.
arXiv:2507. 15356v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions.
The paper introduces DCRL (Divide-and-Conquer RL), a method that recursively decomposes offline goal-conditioned reinforcement learning trajectories into a balanced binary tree. By training values from the leaves up to the root, DCRL avoids noisy max-based backups and reduces bootstrap depth from linear to logarithmic, thereby limiting error accumulation. Experiments on diverse goal-reaching tasks show that DCRL outperforms prior flat offline GCRL methods, achieving a higher average score on the most challenging long-horizon OGBench tasks.
arXiv:2606. 15333v1 Announce Type: cross Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility.
Open-MOPD addresses the capability imbalance problem in multi-teacher on-policy distillation (M-OPD) by isolating capability integration from routing ambiguity and revealing a 35.6% headroom gap compared to a domain-routed oracle ensemble. The study identifies three key factors—sequence-length disparities, convergence drift, and reward staleness—that misallocate token-level optimization budgets, leading to severe degradation in concise tasks. The proposed Open-MOPD framework introduces token-share balancing, gap-aware dynamic budget allocation, and student reward refresh, boosting headroom recovery to 83.4% and providing an open-source, reproducible post‑training recipe and evaluation suite.
HorizonFlow is a hierarchical planner for offline goal-conditioned reinforcement learning that treats the planning horizon as an output rather than a fixed input. It uses a subgoal route planner and an action-prefix controller, both employing insertion-based generation and flow matching, to jointly generate continuous plan content and its length. The method leverages the partially generated plan to guide token insertion and to steer generation toward shorter plans, achieving superior performance on Maze2D, Multi2D, and OGBench benchmarks.
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...