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 19

Vero: An Open RL Recipe for General Visual Reasoning

arXiv:2604. 04917v3 Announce Type: replace-cross Abstract: What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks?

By Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu

llms reinforcement-learning efficiency multimodal benchmarks

arXiv Machine Learning

Jun 19

Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random

arXiv:2606. 20206v1 Announce Type: cross Abstract: In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values.

By Ziheng Wei, Annie Qu, Rui Miao

reinforcement-learning safety

arXiv AI

Jun 19

CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion

arXiv:2606. 19633v1 Announce Type: cross Abstract: Perceptive legged locomotion over discontinuous terrain (e.

By Francisco Affonso, Matheus P. Angarola, Ana Luiza Mineiro, Aditya Potnis, Marcelo Becker, Girish Chowdhary

reinforcement-learning robotics efficiency

arXiv Machine Learning

Jun 19

Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning

arXiv:2606. 19481v1 Announce Type: new Abstract: Offline reinforcement learning (ORL) offers the potential to improve the quality of clinical decision-making using historical electronic health record (EHR) data.

By Thomas Frost, Steve Harris

reinforcement-learning

arXiv Machine Learning

Jun 19

Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning

arXiv:2606. 19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model.

By Ananya Kunisetty, Avishek Ghosh

agents reinforcement-learning benchmarks safety

arXiv AI

Jun 19

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

arXiv:2606. 20280v1 Announce Type: cross Abstract: Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR).

By Yuhan Liu, Pei Fu, Hang Li, Yukun Qi, Chao Jiang, Jingwen Fu, Zhen Liu, Bin Qin, Zhenbo Luo, Jian Luan, Jingmin Xin

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 19

Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models

arXiv:2606. 19750v1 Announce Type: cross Abstract: Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization.

By Darrien McKenzie, Nicklas Hansen, Xiaolong Wang

llms reinforcement-learning

arXiv AI

Jun 19

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

arXiv:2606. 19632v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets.

By Ahmad Farooq, Kamran Iqbal

agents reinforcement-learning robotics efficiency safety

arXiv AI

Jun 19

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

arXiv:2606. 20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context.

By Yanxi Chen, Weijie Shi, Yuexiang Xie, Boyi Hu, Yaliang Li, Bolin Ding, Jingren Zhou

llms agents reinforcement-learning

arXiv Machine Learning

Jun 19

Utility-Aware DRL-Based TXOP Adaptation for NR-U and Wi-Fi Coexistence Networks

arXiv:2605. 00457v4 Announce Type: replace-cross Abstract: The coexistence of NR-U and Wi-Fi in the unlicensed spectrum introduces a challenging resource management problem, where heterogeneous channel access mechanisms can lead to unbalanced spectrum utilization and severe Wi-Fi performance degradation.

By Po-Heng Chou, Yi-Fang Yu, Shou-Yu Chen, Chiapin Wang

reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Jun 19

EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning

arXiv:2510. 19893v2 Announce Type: replace Abstract: Medical AI systems demonstrated impressive diagnostic performance, yet they routinely show uneven accuracy across demographic groups, disadvantaging underrepresented populations.

By Shiqi Dai, Wei Dai, Jiaee Cheong, Paul Pu Liang

reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Jun 19

Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones

arXiv:2505. 18201v2 Announce Type: replace-cross Abstract: Controlling flapping-wing drones requires controllers that handle time-varying, nonlinear, underactuated dynamics from incomplete, noisy sensor data.

By Romain Poletti, Lorenzo Schena, Lilla Koloszar, Joris Degroote, Miguel Alfonso Mendez

agents reinforcement-learning robotics fine-tuning

arXiv AI

Jun 19

A Multi-Agent system for Multi-Objective constrained optimization

arXiv:2606. 20236v1 Announce Type: new Abstract: Many decision-making problems in computing and networking systems can be naturally formulated as cost-minimization problems under performance constraints.

By Federica Filippini

rag agents reinforcement-learning

arXiv AI

Jun 19

Augmenting Game AI with Deep Reinforcement Learning

arXiv:2606. 20210v1 Announce Type: new Abstract: Immersion in video games depends not only on graphics, audio, and game mechanics, but also on the quality of in-game characters.

By Alessandro Sestini, Joakim Bergdahl, Amir Baghi, Jean-Philippe Barrette-LaPierre, Florian Fuchs, Linus Gissl\'en

agents reinforcement-learning

arXiv AI

Jun 19

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

arXiv:2606. 19357v1 Announce Type: cross Abstract: We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen.

By Khurram Javed, Joseph Modayil, Gloria Kennickell, Richard S. Sutton, John Carmack

reinforcement-learning robotics

arXiv AI

Jun 19

Which Pairs to Compare for LLM Post-Training?

arXiv:2606. 19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models.

By Jiangze Han, Vineet Goyal, Will Ma

llms reinforcement-learning benchmarks

arXiv AI

Jun 19

MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

arXiv:2506. 14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied.

By Tristan Tomilin, Luka van den Boogaard, Samuel Garcin, Constantin Ruhdorfer, Bram Grooten, Fabrice Kusters, Yali Du, Andreas Bulling, Mykola Pechenizkiy, Meng Fang

agents reinforcement-learning benchmarks

arXiv AI

Jun 19

Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing

arXiv:2606. 20087v1 Announce Type: new Abstract: Additive manufacturing process optimization requires precise parameter control to minimize defects such as porosity.

By Kianoush Aqabakee, Leonardo Stella

agents reinforcement-learning

arXiv Machine Learning

Jun 19

Comparative Study on Agility, Efficiency, and Impact Absorption of Bipedal Robots with Active Toes

arXiv:2606. 19699v1 Announce Type: cross Abstract: Human legs exhibit high efficiency, agility, and impact absorption, with toes playing a crucial role in these capabilities.

By Joong-Gil Kim, Wontae Ye, Geunwoo Cho, Seong-Ho Yun, Se-Hyoung Cho, Yong-Jae Kim

reinforcement-learning robotics benchmarks

arXiv AI

Jun 19

PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification

arXiv:2602. 00510v2 Announce Type: replace Abstract: Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness.

By Huanghaohe Zou, Peng Han, Emad Nazerian, Mafu Zhang, Zhicheng Guo, Alex Q. Huang

llms reinforcement-learning benchmarks

Get the daily briefing