Imagen de Portada

DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Long, Zhou, Zhijian, Wang, Tianyi, Xu, Weidi, Huang, Zuming, Chu, Wei, Wang, Zhe, Pan, Shirui, Qu, Chao, Qi, Yuan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
por: Li, Long, et al.
Publicado: (2025)

SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
por: Li, Long, et al.
Publicado: (2026)

Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning
por: Wang, Zuo, et al.
Publicado: (2025)

The Representation Jensen-Shannon Divergence
por: Hoyos-Osorio, Jhoan K., et al.
Publicado: (2023)

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
por: Wang, Haozhe, et al.
Publicado: (2025)

Metrization of powers of the Jensen-Shannon divergence
por: Okamura, Kazuki
Publicado: (2023)

Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning
por: Zhang, Xuan, et al.
Publicado: (2025)

Multiclass Local Calibration with the Jensen-Shannon Distance
por: Barbera, Cesare, et al.
Publicado: (2025)

Quantifying magic via quantum $(α,β)$ Jensen-Shannon divergence
por: Wang, Linmao, et al.
Publicado: (2026)

Two tales for a geometric Jensen--Shannon divergence
por: Nielsen, Frank
Publicado: (2025)

JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models
por: Bill, Eric Tillmann, et al.
Publicado: (2025)

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
por: Xu, Shuyao, et al.
Publicado: (2025)

Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards
por: Guo, Kai-Yuan, et al.
Publicado: (2026)

Text-to-3D Generation using Jensen-Shannon Score Distillation
por: Do, Khoi, et al.
Publicado: (2025)

Geometric Jensen-Shannon Divergence Between Gaussian Measures On Hilbert Space
por: Quang, Minh Ha, et al.
Publicado: (2025)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
por: Wen, Xumeng, et al.
Publicado: (2025)

Verifiable Process Rewards for Agentic Reasoning
por: Yuan, Huining, et al.
Publicado: (2026)

Jensen-Shannon Divergence Based Novel Loss Functions for Bayesian Neural Networks
por: Thiagarajan, Ponkrshnan, et al.
Publicado: (2022)

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
por: Guo, Xu, et al.
Publicado: (2025)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
por: Cai, Xin-Qiang, et al.
Publicado: (2025)

To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization
por: Wang, Haozhe, et al.
Publicado: (2025)

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
por: Zhao, Kaiyan, et al.
Publicado: (2024)

Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning
por: Dorent, Reuben, et al.
Publicado: (2025)

Quantum speed limits based on Jensen-Shannon and Jeffreys divergences for general physical processes
por: de Sousa, Jucelino Ferreira, et al.
Publicado: (2025)

Spatial Jensen–Shannon Divergence: A Local, Multiscalar Measure of Multigroup Compositional Dissimilarity
por: Massimo Mucciardi
Publicado: (2026)

A continuous symmetry breaking measure for finite clusters using Jensen-Shannon divergence
por: Lan, Ling, et al.
Publicado: (2024)

Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence
por: Chen, Shuangyi, et al.
Publicado: (2025)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
por: Lu, Xiaodong, et al.
Publicado: (2026)

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents
por: Wang, Peisong, et al.
Publicado: (2025)

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards
por: Zhang, Xuan, et al.
Publicado: (2025)

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
por: Liu, Xiaoyuan, et al.
Publicado: (2025)

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
por: Huang, Guanhua, et al.
Publicado: (2025)

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
por: Gunjal, Anisha, et al.
Publicado: (2025)

Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
por: Li, Ruizhe, et al.
Publicado: (2025)

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
por: Jiang, Yuxin, et al.
Publicado: (2026)

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
por: Wang, Baode, et al.
Publicado: (2025)

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
por: Wang, Baode, et al.
Publicado: (2025)

Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards
por: Wang, Zhen, et al.
Publicado: (2025)

R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning
por: Jiang, Zhizheng, et al.
Publicado: (2026)

Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought
por: Tan, Xiaoyu, et al.
Publicado: (2024)