MInTRL (Minimal Intervention Reinforcement Learning) expands exploration in on-policy reinforcement learning by inserting sparse, local corrections into rollouts via a judge-intervention policy. These interventions replace erroneous suffixes and immediately return control to the main policy, allowing the agent to explore beyond its natural trajectory while maintaining on-policy data. The method uses a sequence-level advantage-regression objective, avoiding importance sampling, and demonstrates superior performance on math and code benchmarks compared to standard on-policy and off-policy baselines.
By Mingyu Chen, Yefan Tao, Gerald Friedland, Xuezhou Zhang, Chris Kong
arXiv:2606. 12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance.
By Haoyuan Deng, Yitong Gao, Yudong Lin, Haichao Liu, Zhenyu Wu, Ziwei Wang
arXiv:2608. 05080v1 Announce Type: new Abstract: Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models.
By Zheyuan Zhang, Manqing Mao, Hong Wang, Zhuoer Wang, Samson Koelle, Jie Yuan, Yanjun Lin, James Feng, Nikki Lijing Kuang, Yanfang Ye, Wei Niu
arXiv:2606. 19476v1 Announce Type: cross Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.
By Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald, Rajai Nasser, Blaise Ag\"uera y Arcas, Jo\~ao Sacramento, Rif A. Saurous, Guillaume Lajoie
arXiv:2603.11321v3 Announce Type: replace-cross
Abstract: Reinforcement Learning with Verifiable Rewards improves reasoning in large language models, yet on-policy learning often suffers from cold-st...
By Yuning Wu, Ke Wang, Haoran Liu, Chaoqun Jia, Devin Chen, Kai Wei
arXiv:2508. 03875v2 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them.
By David Mguni, Wanrong Yang, Jing Dong, Ziquan Liu, Muhammad Salman Haleem, Baoxiang Wang, Dominik Wojtczak
arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.
By Octavio Pappalardo
arXiv:2504. 12557v3 Announce Type: replace-cross Abstract: Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured.
By Siow Meng Low, Ze Gong, Akshat Kumar
arXiv:2606. 09825v1 Announce Type: cross Abstract: Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation.
By Anton Bolychev, Georgiy Malaniya, Sinan Ibrahim, Pavel Osinenko
arXiv:2604. 12645v2 Announce Type: replace-cross Abstract: Although autonomous underwater vehicles promise the capability of marine ecosystem monitoring, their deployment is fundamentally limited by the difficulty of controlling vehicles under highly uncertain and non-stationary underwater dynamics.
By Melvin Laux, Yi-Ling Liu, Rina Alo, S\"oren T\"opper, Mariela De Lucas Alvarez, Frank Kirchner, Rebecca Adam
The paper introduces the Viability‑constrained Behavioral Steering Attack (V‑BSA), a new attack strategy for federated reinforcement learning that targets the timing of interventions rather than just the construction of malicious updates. By selecting sparse intervention states based on local policy uncertainty and applying envelope‑constrained steering, V‑BSA can significantly degrade performance on discrete‑action benchmarks while using far fewer interventions than traditional dense poisoning attacks. The study demonstrates that the specific states at which interventions occur constitute a distinct and critical dimension of robustness in sequential decision‑making settings.
By Shutong Zheng, Sijia Chen
arXiv:2609.38178v1 Announce Type: cross
Abstract: Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this i...
By Zihang Rui, Renhao Wang, Haoxu Huang, Yang Gao