Imagen de Portada

Unified theory of upper confidence bound policies for bandit problems targeting total reward, maximal reward, and more

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kikkawa, Nobuaki, Ohno, Hiroshi
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Leveraging heterogeneous spillover in maximizing contextual bandit rewards
por: Faruk, Ahmed Sayeed, et al.
Publicado: (2023)

Materials Discovery using Max K-Armed Bandit
por: Kikkawa, Nobuaki, et al.
Publicado: (2022)

Trading off rewards and errors in multi-armed bandits
por: Erraqabi, Akram, et al.
Publicado: (2026)

Covariance-adapting algorithm for semi-bandits with application to sparse rewards
por: Perrault, Pierre, et al.
Publicado: (2026)

Agent-centric learning: from external reward maximization to internal knowledge curation
por: Zhou, Hanqi, et al.
Publicado: (2025)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
por: Liu, Shih-Yang, et al.
Publicado: (2026)

Finding good policies in average-reward Markov Decision Processes without prior knowledge
por: Tuynman, Adrienne, et al.
Publicado: (2024)

Logarithmic regret bounds for continuous-time average-reward Markov decision processes
por: Gao, Xuefeng, et al.
Publicado: (2022)

Active teacher selection for reward learning
por: Freedman, Rachel, et al.
Publicado: (2023)

Self-rewarding correction for mathematical reasoning
por: Xiong, Wei, et al.
Publicado: (2025)

Noise-based reward-modulated learning
por: Fernández, Jesús García, et al.
Publicado: (2025)

Approximate information maximization for bandit games
por: Barbier-Chebbah, Alex, et al.
Publicado: (2023)

Meta Flow Maps enable scalable reward alignment
por: Potaptchik, Peter, et al.
Publicado: (2026)

LIRE: listwise reward enhancement for preference alignment
por: Zhu, Mingye, et al.
Publicado: (2024)

Revealing graph bandits for maximizing local influence
por: Carpentier, Alexandra, et al.
Publicado: (2026)

The impact of intrinsic rewards on exploration in Reinforcement Learning
por: Kayal, Aya, et al.
Publicado: (2025)

Continuously evolving rewards in an open-ended environment
por: Bailey, Richard M.
Publicado: (2024)

Optimistic Q-learning for average reward and episodic reinforcement learning
por: Agrawal, Priyank, et al.
Publicado: (2024)

Scale-free adaptive planning for deterministic dynamics & discounted rewards
por: Bartlett, Peter L., et al.
Publicado: (2026)

Physics-based reward driven image analysis in microscopy
por: Barakati, Kamyar, et al.
Publicado: (2024)

Episodic Reinforcement Learning with Expanded State-reward Space
por: Liang, Dayang, et al.
Publicado: (2024)

EVAL: EigenVector-based Average-reward Learning
por: Adamczyk, Jacob, et al.
Publicado: (2025)

Streaming Looking Ahead with Token-level Self-reward
por: Zhang, Hongming, et al.
Publicado: (2025)

Approximate optimality and the risk/reward tradeoff in a class of bandit problems
por: Chen, Zengjing, et al.
Publicado: (2022)

Integration of Scanning Probe Microscope with High-Performance Computing: fixed-policy and reward-driven workflows implementation
por: Liu, Yu, et al.
Publicado: (2024)

Risk-averse Total-reward MDPs with ERM and EVaR
por: Su, Xihong, et al.
Publicado: (2024)

reward-lens: A Mechanistic Interpretability Library for Reward Models
por: Nadaf, Mohammed Suhail B
Publicado: (2026)

Risk and optimal policies in bandit experiments
por: Adusumilli, Karun
Publicado: (2021)

TractOracle: towards an anatomically-informed reward function for RL-based tractography
por: Théberge, Antoine, et al.
Publicado: (2024)

Conformal Bandits: Bringing statistical validity and reward efficiency to the small-gap regime
por: Cuonzo, Simone, et al.
Publicado: (2025)

Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations
por: Baumann, Dominik, et al.
Publicado: (2023)

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
por: Moitra, Ankur, et al.
Publicado: (2026)

Stochastic first-order methods for average-reward Markov decision processes
por: Li, Tianjiao, et al.
Publicado: (2022)

BLEUBERI: BLEU is a surprisingly effective reward for instruction following
por: Chang, Yapei, et al.
Publicado: (2025)

Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
por: He, Jianliang, et al.
Publicado: (2024)

Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models
por: Zhang, Zizhuo, et al.
Publicado: (2025)

Leveraging LLMs for reward function design in reinforcement learning control tasks
por: Cardenoso, Franklin, et al.
Publicado: (2025)

Steering diffusion models with quadratic rewards: a fine-grained analysis
por: Moitra, Ankur, et al.
Publicado: (2026)

Lookahead identification in adversarial bandits: accuracy and memory bounds
por: Brukhim, Nataly, et al.
Publicado: (2026)

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
por: Arnal, Charles, et al.
Publicado: (2025)