The paper introduces Safe Contrastive Reinforcement Learning (Safe-CRL), a method that corrects bias in contrastive RL caused by failure-terminated Markov decision processes. By applying mass-weighted InfoNCE and a log-survival-mass score, Safe-CRL uses only a one-bit failure signal to improve survival and goal-reaching performance across twelve robot navigation and locomotion tasks. The approach demonstrates complex failure-avoidance behaviors and completes the theoretical foundation of contrastive RL under failure termination.
By Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu
The paper investigates data‑driven predictive maintenance where health‑condition estimation is coupled with an ordering‑replacement decision model. It shows that the traditional Estimate‑Then‑Optimize (ETO) approach can lead to inconsistent, suboptimal decisions and introduces an Integrated Estimate‑Optimize (IEO) framework that directly optimizes maintenance cost, bypassing conventional accuracy metrics. Experiments on CMAPSS data demonstrate that IEO reduces mean maintenance cost by 14.8–22.7% versus ETO and 7.2–11.8% versus a decision‑oriented baseline, while also lowering failure rates and cost variability, even when prediction errors are higher.
By Zhuojun Xie, Adam Abdin, Yiping Fang
The paper introduces Potential-Guided Policy Optimization (PGPO), a method for multi-turn agentic tasks that improves credit assignment by estimating empirical state potentials from anchor-state-group return statistics. PGPO derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation and finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong performance compared to recent group-based reinforcement learning methods, with negligible training overhead.
By Yuyao Zheng, Haipeng Sun, Junwei Bao, Lemao Liu, Hongfei Jiang, Yang Song, Dejing Dou
arXiv:2605.17036v4 Announce Type: replace-cross
Abstract: This paper studies the performance and reliability of autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game....
By Carol Xuan Long, David Simchi-Levi, Feng Zhu, Huangyuan Su, Andre P. Calmon, Flavio P. Calmon
The paper introduces Milestone Viability Potential Policy Optimization (MVPO), a reinforcement learning algorithm designed for long‑horizon large language model agents. MVPO addresses the zero‑credit failure problem by learning from viable failure prefixes, estimating prefix potential over Union‑Find viability regions, and repairing zero‑credit groups with potential‑difference advantages. Experiments on Qwen2.5‑1.5B‑Instruct demonstrate that MVPO outperforms eight strong baselines, improving success rates on ALFWorld and WebShop with minimal overhead.
By Qi Zhou, Yuanfan Li
arXiv:2407. 15283v2 Announce Type: replace-cross Abstract: Industry is moving toward autonomous, network-connected machines that detect and adapt to changing conditions, including hardware faults.
By Sheila Schoepp, Mehran Taghian, Shotaro Miwa, Yoshihiro Mitsuka, Shadan Golestan, Osmar Za\"iane
arXiv:2606. 18820v1 Announce Type: cross Abstract: Sequential decision problems often exhibit an asymmetric evolution of information and decision flexibility: as a decision cycle unfolds, the agent receives richer information while feasible actions expire due to operational cutoffs, commitments, or resource constraints.
By Jiaxi Liu, Aiping Yang, Yuhang Yang, Shuqi Zhang, Zewei Dong, Jiangming Yang, Xuebin Chen
The paper introduces the Distinguish-or-Homogenize principle, where an agent can either spend resources to differentiate between latent fault models or alter the system state so that the remaining models share a common acceptable policy, eliminating further diagnosis. This leads to the Last-Chance Policy Identification (LCPI) framework, which evaluates correctness at the reached state rather than the initial one, and defines the Last Identifiable Margin (LIM) as the boundary between distinguishing and homogenizing. For deterministic diagnostic graphs, an Exact-LIM recursion is provided, while for noisy finite-horizon recovery the authors propose Risk-Budgeted Compatibility Planning (RBCP), which searches a compatibility-aware frontier under a hard worst-case failure constraint, demonstrating improved risk-feasible recovery in microservice and MiniGrid scenarios.
By Yibo Guo, Xiaodan Wang
The paper introduces a preference-conditioned multi-objective reinforcement learning framework for tactical decision making in heavy-duty vehicles. It explicitly models safety, energy efficiency, and time efficiency as separate objectives and uses Generalized Policy Improvement and Proximal Policy Optimization to learn policies that approximate the Pareto front across these conflicting goals. Experiments in a scalable highway traffic simulation show smooth, interpretable Pareto fronts and meaningful trade-offs, with the policy enabling behavior transitions without retraining.
By Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani
arXiv:2608. 14122v1 Announce Type: new Abstract: Production scheduling in complex manufacturing environments is challenging when sequence-dependent setup times, stochastic disturbances, and due-date constraints must be addressed simultaneously.
By Arne Kr\"oger, Ralf Buscherm\"ohle, Wilhelm Hasselbring, Henrik Wilbers
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks proposes a new reinforcement learning approach that estimates empirical state potentials from anchor-state-group return statistics within each rollout group. By deriving action advantages from potential differences between adjacent states, PGPO enables cross‑trajectory credit propagation, providing finer‑grained step‑level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong overall performance compared to recent group‑based RL methods, with negligible training overhead.
arXiv:2607. 23434v1 Announce Type: cross Abstract: Unexpected shocks recur in global operations, requiring decision rules that adapt as market and operating conditions change.
By Young Hyun Cho, Franz Stoll, Will Wei Sun, Guang Lin, Stephan Biller