Copertina

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Mingze, Anand, Abhinav, Verma, Shweta, Mezini, Mira
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CodeSSM: Towards State Space Models for Code Understanding
di: Verma, Shweta, et al.
Pubblicazione: (2025)

A Critical Study of What Code-LLMs (Do Not) Learn
di: Anand, Abhinav, et al.
Pubblicazione: (2024)

Towards Understanding What State Space Models Learn About Code
di: Wu, Jiali, et al.
Pubblicazione: (2026)

Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
di: Sakharova, Marina, et al.
Pubblicazione: (2025)

Analysis of Long Range Dependency Understanding in State Space Models
di: Ravikumar, Srividya, et al.
Pubblicazione: (2026)

Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
di: Jolfaei, Erfan Aghadavoodi, et al.
Pubblicazione: (2026)

Automating the Refinement of Reinforcement Learning Specifications
di: Ambadkar, Tanmay, et al.
Pubblicazione: (2025)

Pre-training with Synthetic Data Helps Offline Reinforcement Learning
di: Wang, Zecheng, et al.
Pubblicazione: (2023)

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
di: Hu, Zican, et al.
Pubblicazione: (2025)

The Generalization Gap in Offline Reinforcement Learning
di: Mediratta, Ishita, et al.
Pubblicazione: (2023)

Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning
di: Cherif, Lynn, et al.
Pubblicazione: (2025)

Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
di: Derstroff, Cedric, et al.
Pubblicazione: (2024)

MAPLE: Modality-Aware Post-training and Learning Ecosystem
di: Verma, Nikhil, et al.
Pubblicazione: (2026)

Sample Efficient Active Algorithms for Offline Reinforcement Learning
di: Roy, Soumyadeep, et al.
Pubblicazione: (2026)

Adaptable Hindsight Experience Replay for Search-Based Learning
di: Vazaios, Alexandros, et al.
Pubblicazione: (2025)

Offline Reinforcement Learning with Generative Trajectory Policies
di: Feng, Xinsong, et al.
Pubblicazione: (2025)

Doubly Mild Generalization for Offline Reinforcement Learning
di: Mao, Yixiu, et al.
Pubblicazione: (2024)

Offline Trajectory Optimization for Offline Reinforcement Learning
di: Zhao, Ziqi, et al.
Pubblicazione: (2024)

When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
di: Liu, Vincent, et al.
Pubblicazione: (2023)

Provable Zero-Shot Generalization in Offline Reinforcement Learning
di: Wang, Zhiyong, et al.
Pubblicazione: (2025)

Imagination-Limited Q-Learning for Offline Reinforcement Learning
di: Liu, Wenhui, et al.
Pubblicazione: (2025)

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
di: Ambadkar, Tanmay, et al.
Pubblicazione: (2026)

Improving Offline Reinforcement Learning with Inaccurate Simulators
di: Hou, Yiwen, et al.
Pubblicazione: (2024)

Pessimistic Auxiliary Policy for Offline Reinforcement Learning
di: Zhang, Fan, et al.
Pubblicazione: (2026)

Policy-regularized Offline Multi-objective Reinforcement Learning
di: Lin, Qian, et al.
Pubblicazione: (2024)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
di: Wu, Yecheng, et al.
Pubblicazione: (2026)

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
di: Huang, Xiao, et al.
Pubblicazione: (2025)

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
di: Lee, Jaewoo, et al.
Pubblicazione: (2024)

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
di: Zheng, Chujie, et al.
Pubblicazione: (2025)

Goal-Conditioned Data Augmentation for Offline Reinforcement Learning
di: Huang, Xingshuai, et al.
Pubblicazione: (2024)

SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance
di: Zhang, Liyu, et al.
Pubblicazione: (2024)

Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research
di: Panda, Sourav, et al.
Pubblicazione: (2026)

CoRe-Code: Collaborative Reinforcement Learning for Code Generation
di: Dou, Zhihao, et al.
Pubblicazione: (2026)

Preference Elicitation for Offline Reinforcement Learning
di: Pace, Alizée, et al.
Pubblicazione: (2024)

Offline Reinforcement Learning with Imbalanced Datasets
di: Jiang, Li, et al.
Pubblicazione: (2023)

Simple Ingredients for Offline Reinforcement Learning
di: Cetin, Edoardo, et al.
Pubblicazione: (2024)

State-Constrained Offline Reinforcement Learning
di: Hepburn, Charles A., et al.
Pubblicazione: (2024)

Dataset Distillation for Offline Reinforcement Learning
di: Light, Jonathan, et al.
Pubblicazione: (2024)

Offline Reinforcement Learning with Imputed Rewards
di: Romeo, Carlo, et al.
Pubblicazione: (2024)

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
di: Park, Jongchan, et al.
Pubblicazione: (2025)