Copertina

Reinforcement Learning via Self-Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hübotter, Jonas, Lübeck, Frederike, Behric, Lejs, Baumann, Anton, Bagatella, Marco, Marta, Daniel, Hakimi, Ido, Shenfeld, Idan, Buening, Thomas Kleine, Guestrin, Carlos, Krause, Andreas
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Aligning Language Models from User Interactions
di: Buening, Thomas Kleine, et al.
Pubblicazione: (2026)

Majority Voting for Code Generation
di: Launer, Tim, et al.
Pubblicazione: (2026)

Self-Distillation Enables Continual Learning
di: Shenfeld, Idan, et al.
Pubblicazione: (2026)

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
di: Hübotter, Jonas, et al.
Pubblicazione: (2024)

Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
di: Otth, Matthias, et al.
Pubblicazione: (2025)

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging
di: Bertolissi, Ryo, et al.
Pubblicazione: (2025)

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
di: Diaz-Bone, Leander, et al.
Pubblicazione: (2025)

Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
di: Hübotter, Jonas, et al.
Pubblicazione: (2025)

Active Fine-Tuning of Multi-Task Policies
di: Bagatella, Marco, et al.
Pubblicazione: (2024)

Test-time Offline Reinforcement Learning on Goal-related Experience
di: Bagatella, Marco, et al.
Pubblicazione: (2025)

Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
di: Pásztor, Barna, et al.
Pubblicazione: (2025)

Probabilistic Artificial Intelligence
di: Krause, Andreas, et al.
Pubblicazione: (2025)

Strategyproof Reinforcement Learning from Human Feedback
di: Buening, Thomas Kleine, et al.
Pubblicazione: (2025)

Environment Design for Inverse Reinforcement Learning
di: Buening, Thomas Kleine, et al.
Pubblicazione: (2022)

Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding
di: Shao, Daqian, et al.
Pubblicazione: (2025)

ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
di: Behric, Lejs Deen, et al.
Pubblicazione: (2025)

Directed Exploration in Reinforcement Learning from Linear Temporal Logic
di: Bagatella, Marco, et al.
Pubblicazione: (2024)

Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
di: Bagatella, Marco, et al.
Pubblicazione: (2026)

A Minimax Approach to Ad Hoc Teamwork
di: Villin, Victor, et al.
Pubblicazione: (2025)

LITE: Efficiently Estimating Gaussian Probability of Maximality
di: Menet, Nicolas, et al.
Pubblicazione: (2025)

RL's Razor: Why Online Reinforcement Learning Forgets Less
di: Shenfeld, Idan, et al.
Pubblicazione: (2025)

Adaptable Cardiovascular Disease Risk Prediction from Heterogeneous Data using Large Language Models
di: Lübeck, Frederike, et al.
Pubblicazione: (2025)

Strategic Linear Contextual Bandits
di: Buening, Thomas Kleine, et al.
Pubblicazione: (2024)

Optimistic Task Inference for Behavior Foundation Models
di: Rupf, Thomas, et al.
Pubblicazione: (2025)

Active Few-Shot Fine-Tuning
di: Hübotter, Jonas, et al.
Pubblicazione: (2024)

Transductive Active Learning: Theory and Applications
di: Hübotter, Jonas, et al.
Pubblicazione: (2024)

TGRL: An Algorithm for Teacher Guided Reinforcement Learning
di: Shenfeld, Idan, et al.
Pubblicazione: (2023)

Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
di: Hübotter, Jonas, et al.
Pubblicazione: (2025)

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
di: Hilel, Almog, et al.
Pubblicazione: (2025)

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
di: Damani, Mehul, et al.
Pubblicazione: (2024)

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
di: Baur, Raphaël, et al.
Pubblicazione: (2026)

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
di: Melikidze, Davit, et al.
Pubblicazione: (2026)

Language Model Personalization via Reward Factorization
di: Shenfeld, Idan, et al.
Pubblicazione: (2025)

JUICER: Data-Efficient Imitation Learning for Robotic Assembly
di: Ankile, Lars, et al.
Pubblicazione: (2024)

RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
di: Yang, Daniel, et al.
Pubblicazione: (2026)

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
di: Aminian, Gholamali, et al.
Pubblicazione: (2025)

Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
di: Puri, Isha, et al.
Pubblicazione: (2026)

Zero-Shot Offline Imitation Learning via Optimal Transport
di: Rupf, Thomas, et al.
Pubblicazione: (2024)

From Imitation to Refinement -- Residual RL for Precise Assembly
di: Ankile, Lars, et al.
Pubblicazione: (2024)

Value Augmented Sampling for Language Model Alignment and Personalization
di: Han, Seungwook, et al.
Pubblicazione: (2024)