Copertina

Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zhaochun, Wang, Chen, Bai, Jionghao, Cui, Shisheng, Lan, Ge, Zhao, Zhou, Wang, Yue
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
di: Wang, Chen, et al.
Pubblicazione: (2025)

Towards a Theoretical Understanding to the Generalization of RLHF
di: Li, Zhaochun, et al.
Pubblicazione: (2026)

DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
di: Li, Xiaofan, et al.
Pubblicazione: (2026)

Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs
di: Wei, Wang, et al.
Pubblicazione: (2025)

Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs
di: Song, Meichen, et al.
Pubblicazione: (2026)

On the Trade-off between Flatness and Optimization in Distributed Learning
di: Cao, Ying, et al.
Pubblicazione: (2024)

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
di: Yao, Xincheng, et al.
Pubblicazione: (2026)

ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning
di: Liu, Bing, et al.
Pubblicazione: (2025)

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
di: Norman, Ben, et al.
Pubblicazione: (2023)

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
di: Salgia, Sudeep, et al.
Pubblicazione: (2025)

DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management
di: Su, Xuerui, et al.
Pubblicazione: (2025)

Neural Exploitation and Exploration of Contextual Bandits
di: Ban, Yikun, et al.
Pubblicazione: (2023)

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
di: Wang, Chen, et al.
Pubblicazione: (2026)

Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
di: Huang, Fanding, et al.
Pubblicazione: (2025)

Accelerating Large-Scale Dataset Distillation via Exploration-Exploitation Optimization
di: Alahmadi, Muhammad J., et al.
Pubblicazione: (2026)

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
di: Liang, Kun, et al.
Pubblicazione: (2026)

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
di: Chen, Zhipeng, et al.
Pubblicazione: (2025)

The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective
di: Yan, Renye, et al.
Pubblicazione: (2024)

In-context Exploration-Exploitation for Reinforcement Learning
di: Dai, Zhenwen, et al.
Pubblicazione: (2024)

Exploitation Is All You Need... for Exploration
di: Rentschler, Micah, et al.
Pubblicazione: (2025)

Provably Efficient Exploration in Policy Optimization
di: Cai, Qi, et al.
Pubblicazione: (2019)

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
di: Bamba, Udbhav, et al.
Pubblicazione: (2025)

Controllable Pareto Trade-off between Fairness and Accuracy
di: Du, Yongkang, et al.
Pubblicazione: (2025)

Architecture Selection via the Trade-off Between Accuracy and Robustness
di: Deng, Zhun, et al.
Pubblicazione: (2019)

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
di: Zeng, Weihao, et al.
Pubblicazione: (2024)

Exploration-Exploitation Tradeoff in Universal Lossy Compression
di: Weinberger, Nir, et al.
Pubblicazione: (2025)

Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
di: Gao, Gong, et al.
Pubblicazione: (2026)

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
di: Zhao, Yang, et al.
Pubblicazione: (2026)

Private Optimal Inventory Policy Learning for Feature-based Newsvendor with Unknown Demand
di: Zhao, Tuoyi, et al.
Pubblicazione: (2024)

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space
di: K, Swaminathan S, et al.
Pubblicazione: (2026)

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
di: Wang, Yue, et al.
Pubblicazione: (2025)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
di: Chen, Peter, et al.
Pubblicazione: (2025)

Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration
di: Yu, Youwei, et al.
Pubblicazione: (2026)

Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
di: Wang, Shixiong, et al.
Pubblicazione: (2023)

Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives
di: Chen, Lin, et al.
Pubblicazione: (2026)

You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
di: Han, Xiaotian, et al.
Pubblicazione: (2025)

Enhancing Trade-offs in Privacy, Utility, and Computational Efficiency through MUltistage Sampling Technique (MUST)
di: Zhao, Xingyuan, et al.
Pubblicazione: (2023)

Structured Exploration and Exploitation of Label Functions for Automated Data Annotation
di: Lam, Phong, et al.
Pubblicazione: (2026)

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
di: Kim, JaeYoon, et al.
Pubblicazione: (2024)

Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration
di: Mhammedi, Zakaria, et al.
Pubblicazione: (2026)