Reinforcement learning

Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.

7,242 stories · RSS feed

arXiv AI

Jun 15

Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs

arXiv:2604. 23841v2 Announce Type: replace-cross Abstract: Efficiently solving the Job Shop Scheduling Problem in real-world industrial applications requires policies that are both computationally lean and topologically robust.

By Jonathan Hoss, Moritz Link, Noah Klarmann

agents diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jun 15

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

arXiv:2604. 18419v5 Announce Type: replace Abstract: LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses.

By Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein, Guy Kushilevitz, Ram Yazdi, Patrick Rebeschini

llms reinforcement-learning safety

arXiv Machine Learning

Jun 15

Diffusion Policy Optimization without Drifting Apart

arXiv:2606. 13795v1 Announce Type: new Abstract: RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement.

By Haozhe Jiang, Haiwen Feng, Pieter Abbeel, Jiantao Jiao, Angjoo Kanazawa, Nika Haghtalab

llms diffusion reinforcement-learning efficiency

arXiv Machine Learning

Jun 15

Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning

arXiv:2606. 14130v1 Announce Type: new Abstract: Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents.

By Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli

agents reinforcement-learning safety

arXiv AI

Jun 15

Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

arXiv:2606. 14409v1 Announce Type: cross Abstract: In this report, we present Hy-Embodied-0.

By He Zhang, Lingzhu Xiang, Haitao Lin, Zeyu Huang, Minghui Wang, Dingyan Zhong, Yubo Dong, Yihao Wu, Yongming Rao, Dongsheng Zhang, Wanjia He, Ling Chen, Kai Huang, Jiahao Chen, Sichang Su, Xumin Yu, Ziyi Wang, Chengwei Zhu, Xiao Teng, Yuchun Guo, Yufeng Zhang, Yuandong Liu, Rui Wang, Zisheng Lu, Han Hu, Zhengyou Zhang

reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Jun 15

Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

arXiv:2511. 07368v3 Announce Type: replace-cross Abstract: Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS).

By Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, Taiji Suzuki

reinforcement-learning

arXiv Machine Learning

Jun 15

Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs

arXiv:2606. 14095v1 Announce Type: new Abstract: We study the sample complexity of learning in average-reward weakly-coupled Markov decision processes (WCMDPs) and Restless Bandits (RBs) under a generative model.

By Tianhao Wu, Matthew Zurek, Weina Wang, Qiaomin Xie

reinforcement-learning safety

arXiv AI

Jun 15

3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding

arXiv:2603. 04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.

By Xiongkun Linghu, Jiangyong Huang, Baoxiong Jia, Siyuan Huang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 15

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

arXiv:2603. 24596v3 Announce Type: replace-cross Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts.

By Di Cao, Dongjie Fu, Hai Yu, Siqi Zheng, Xu Tan, Tao Jin

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jun 15

CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning

arXiv:2606. 14415v1 Announce Type: new Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs).

By Ayoub Belouadah, Sylvain Kubler, Yves Le Traon

reinforcement-learning robotics benchmarks safety

arXiv AI

Jun 15

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

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

agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 15

When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks

arXiv:2606. 14629v1 Announce Type: cross Abstract: Verifier-driven self-DPO is a common recipe for self-improving production visual-language models.

By Jianzhe Lin

llms reinforcement-learning

arXiv AI

Jun 15

Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

arXiv:2602. 14169v2 Announce Type: replace-cross Abstract: Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space.

By Yiran Guo, Zhongjian Qiao, Yingqi Xie, Jie Liu, Dan Ye, Ruiqing Zhang, Shuang Qiu, Lijie Xu

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 15

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

arXiv:2507. 20068v2 Announce Type: replace Abstract: Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment.

By Aishwarya Mandyam, Jason Meng, Ge Gao, Jiankai Sun, Mac Schwager, Barbara E. Engelhardt, Emma Brunskill

reinforcement-learning robotics

arXiv Machine Learning

Jun 15

Temporally Consistent Graph Q-Networks for Intelligent Network Control

arXiv:2606. 13848v1 Announce Type: cross Abstract: Mobile networks continue to grow in complexity and next generation networks are expected to support both increasing traffic loads and more diverse services.

By Zacharias Veiksaar, Maxime Bouton

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 15

Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study

arXiv:2606. 12881v2 Announce Type: replace-cross Abstract: We present an approach to fine-tuning large language models using Direct Preference Optimization (DPO), a reinforcement learning technique.

By Dezhi Yu, Yvonne Qiu, ShuoJia Fu

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 15

Provably Safe, Yet Scalable Reinforcement Learning

arXiv:2606. 14536v1 Announce Type: new Abstract: Safe reinforcement learning (RL) aims to learn policies that optimize rewards while satisfying constraints.

By Kai S. Yun, Zeyang Li, Navid Azizan

reinforcement-learning robotics safety

arXiv Machine Learning

Jun 15

Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals

arXiv:2606. 14650v1 Announce Type: new Abstract: The identification of optimal structures within vast arrays of interconnected data necessitates significant sampling- and computational effort.

By Christoph Bauschmann, Setareh Maghsudi

reinforcement-learning

arXiv AI

Jun 15

ANSR-DT: A Neuro-Symbolic Framework for Adaptive and Explainable Digital Twins

arXiv:2501. 08561v4 Announce Type: replace Abstract: Digital twins are increasingly used to monitor and optimize industrial systems, yet many existing frameworks remain difficult to interpret, slow to adapt, and limited in their ability to incorporate explicit domain knowledge.

By Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez, Houbing Herbert Song

reinforcement-learning benchmarks safety

arXiv AI

Jun 15

UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems

arXiv:2606. 13683v1 Announce Type: new Abstract: To address the challenge that current dialogue policy planning methods struggle to dynamically adapt to diverse user characteristics, this paper proposes a User Portrait based Nested Rollout Policy Adaptation (UP-NRPA) online framework with Large Language Models.

By Hui Wang, Fafa Zhang, Meng Liu, Xiangyu Chen, Chaoxu Mu

llms reinforcement-learning benchmarks

Get the daily briefing