Imagen de Portada

A Theoretical Framework for Partially Observed Reward-States in RLHF

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kausik, Chinmaya, Mutti, Mirco, Pacchiano, Aldo, Tewari, Ambuj
Formato:	Preprint
Publicado:	2024
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

Leveraging Offline Data in Linear Latent Contextual Bandits
por: Kausik, Chinmaya, et al.
Publicado: (2024)

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
por: Hong, Kihyuk, et al.
Publicado: (2025)

The Context Gathering Decision Process: A POMDP Framework for Agentic Search
por: Kausik, Chinmaya, et al.
Publicado: (2026)

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
por: Russo, Alessio, et al.
Publicado: (2025)

Second Order Bounds for Contextual Bandits with Function Approximation
por: Pacchiano, Aldo
Publicado: (2024)

Active Preference Optimization for Sample Efficient RLHF
por: Das, Nirjhar, et al.
Publicado: (2024)

Reward Model Overoptimisation in Iterated RLHF
por: Wolf, Lorenz, et al.
Publicado: (2025)

State-free Reinforcement Learning
por: Chen, Mingyu, et al.
Publicado: (2024)

Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives
por: Afshar, Aida, et al.
Publicado: (2024)

Compute Aligned Training: Optimizing for Test Time Inference
por: Ousherovitch, Adam, et al.
Publicado: (2026)

Improved Training Mechanism for Reinforcement Learning via Online Model Selection
por: Afshar, Aida, et al.
Publicado: (2025)

How to Explore with Belief: State Entropy Maximization in POMDPs
por: Zamboni, Riccardo, et al.
Publicado: (2024)

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
por: Zhang, Chen Bo Calvin, et al.
Publicado: (2024)

Information-Theoretic Reward Decomposition for Generalizable RLHF
por: Mao, Liyuan, et al.
Publicado: (2025)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
por: Miao, Yuchun, et al.
Publicado: (2024)

Towards Principled Unsupervised Multi-Agent Reinforcement Learning
por: Zamboni, Riccardo, et al.
Publicado: (2025)

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
por: Misra, Dipendra, et al.
Publicado: (2026)

Data-Driven Online Model Selection With Regret Guarantees
por: Pacchiano, Aldo, et al.
Publicado: (2023)

In-Context Learning for Pure Exploration
por: Russo, Alessio, et al.
Publicado: (2025)

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching
por: Fraschini, Andrea, et al.
Publicado: (2026)

Multiple-policy Evaluation via Density Estimation
por: Chen, Yilei, et al.
Publicado: (2024)

Experiment Planning with Function Approximation
por: Pacchiano, Aldo, et al.
Publicado: (2024)

From Parameters to Behaviors: Unsupervised Compression of the Policy Space
por: Tenedini, Davide, et al.
Publicado: (2025)

Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF
por: Liu, Jing
Publicado: (2025)

RLHF Workflow: From Reward Modeling to Online RLHF
por: Dong, Hanze, et al.
Publicado: (2024)

Reward Shaping to Mitigate Reward Hacking in RLHF
por: Fu, Jiayi, et al.
Publicado: (2025)

Reward-Robust RLHF in LLMs
por: Yan, Yuzi, et al.
Publicado: (2024)

CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
por: Wang, Hao, et al.
Publicado: (2026)

Reward Compatibility: A Framework for Inverse RL
por: Lazzati, Filippo, et al.
Publicado: (2025)

Policy Filtration for RLHF to Mitigate Noise in Reward Models
por: Zhang, Chuheng, et al.
Publicado: (2024)

In-Context Learning for Pure Exploration in Continuous Spaces
por: Russo, Alessio, et al.
Publicado: (2026)

Provable Interactive Learning with Hindsight Instruction Feedback
por: Misra, Dipendra, et al.
Publicado: (2024)

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
por: Baharav, Tavor Z., et al.
Publicado: (2025)

How to Evaluate Reward Models for RLHF
por: Frick, Evan, et al.
Publicado: (2024)

A Characterization of List Language Identification in the Limit
por: Charikar, Moses, et al.
Publicado: (2025)

Generalisation of RLHF under Reward Shift and Clipped KL Regularisation
por: Tang, Kenton, et al.
Publicado: (2026)

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
por: Zhao, Kangwen, et al.
Publicado: (2025)

Quantile Regression for Distributional Reward Models in RLHF
por: Dorka, Nicolai
Publicado: (2024)

ODIN: Disentangled Reward Mitigates Hacking in RLHF
por: Chen, Lichang, et al.
Publicado: (2024)

Accelerating RLHF Training with Reward Variance Increase
por: Yang, Zonglin, et al.
Publicado: (2025)