Imagen de Portada

All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Swamy, Gokul, Choudhury, Sanjiban, Sun, Wen, Wu, Zhiwei Steven, Bagnell, J. Andrew
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Inverse Reinforcement Learning without Reinforcement Learning
por: Swamy, Gokul, et al.
Publicado: (2023)

The Virtues of Pessimism in Inverse Reinforcement Learning
por: Wu, David, et al.
Publicado: (2024)

Hybrid Inverse Reinforcement Learning
por: Ren, Juntao, et al.
Publicado: (2024)

Efficient Imitation under Misspecification
por: Espinosa-Dice, Nicolas, et al.
Publicado: (2025)

The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
por: Song, Yuda, et al.
Publicado: (2024)

Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
por: Tang, Jingwu, et al.
Publicado: (2024)

Accelerating Inverse Reinforcement Learning with Expert Bootstrapping
por: Wu, David, et al.
Publicado: (2024)

Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning
por: Zhang, Jiahao, et al.
Publicado: (2026)

A Minimaximalist Approach to Reinforcement Learning from Human Feedback
por: Swamy, Gokul, et al.
Publicado: (2024)

Process Reward Models for LLM Agents: Practical Framework and Directions
por: Choudhury, Sanjiban
Publicado: (2025)

A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
por: Jain, Arnav Kumar, et al.
Publicado: (2025)

Aligning LLMs with Domain Invariant Reward Models
por: Wu, David, et al.
Publicado: (2025)

REBEL: Reinforcement Learning via Regressing Relative Rewards
por: Gao, Zhaolin, et al.
Publicado: (2024)

Hybrid Reinforcement Learning from Offline Observation Alone
por: Song, Yuda, et al.
Publicado: (2024)

Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning
por: Sutawika, Lintang, et al.
Publicado: (2026)

Diffusing States and Matching Scores: A New Framework for Imitation Learning
por: Wu, Runzhe, et al.
Publicado: (2024)

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning
por: Song, Yuda, et al.
Publicado: (2025)

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
por: Choudhury, Sanjiban, et al.
Publicado: (2024)

Imitation Learning from a Single Temporally Misaligned Video
por: Huey, William, et al.
Publicado: (2025)

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
por: Jain, Arnav Kumar, et al.
Publicado: (2024)

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
por: Wu, Yilin, et al.
Publicado: (2025)

Expanding the Capabilities of Reinforcement Learning via Text Feedback
por: Song, Yuda, et al.
Publicado: (2026)

ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
por: Wang, Ruoyu, et al.
Publicado: (2024)

Distilling Realizable Students from Unrealizable Teachers
por: Kim, Yujin, et al.
Publicado: (2025)

Supervised Fine-Tuning as Inverse Reinforcement Learning
por: Sun, Hao
Publicado: (2024)

Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
por: Ren, Juntao, et al.
Publicado: (2025)

Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions
por: Li, Zhaoyi, et al.
Publicado: (2025)

Maximum Likelihood Reinforcement Learning
por: Tajwar, Fahim, et al.
Publicado: (2026)

Your Learned Constraint is Secretly a Backward Reachable Tube
por: Qadri, Mohamad, et al.
Publicado: (2025)

InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions
por: Kedia, Kushal, et al.
Publicado: (2023)

Imitation Learning via Focused Satisficing
por: Shah, Rushit N., et al.
Publicado: (2025)

Neural Likelihood Approximation for Integer Valued Time Series Data
por: O'Loughlin, Luke, et al.
Publicado: (2023)

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
por: Wang, Jingyao, et al.
Publicado: (2025)

Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG
por: Zhang, Yicheng, et al.
Publicado: (2026)

EvIL: Evolution Strategies for Generalisable Imitation Learning
por: Sapora, Silvia, et al.
Publicado: (2024)

Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner
por: Ma, Hao, et al.
Publicado: (2026)

MARFT: Multi-Agent Reinforcement Fine-Tuning
por: Liao, Junwei, et al.
Publicado: (2025)

Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
por: Jia, Zhiwei, et al.
Publicado: (2024)

One-Shot Imitation under Mismatched Execution
por: Kedia, Kushal, et al.
Publicado: (2024)

Expressive Value Learning for Scalable Offline Reinforcement Learning
por: Espinosa-Dice, Nicolas, et al.
Publicado: (2025)