Copertina

Behavior Injection: Preparing Language Models for Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cen, Zhepeng, Yao, Yihang, Han, William, Liu, Zuxin, Zhao, Ding
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
di: Yao, Yihang, et al.
Pubblicazione: (2023)

Learning from Sparse Offline Datasets via Conservative Density Estimation
di: Cen, Zhepeng, et al.
Pubblicazione: (2024)

Feasibility Consistent Representation Learning for Safe Reinforcement Learning
di: Cen, Zhepeng, et al.
Pubblicazione: (2024)

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
di: Yao, Yihang, et al.
Pubblicazione: (2026)

Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving
di: Lin, Haohong, et al.
Pubblicazione: (2023)

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
di: Liu, Zuxin, et al.
Pubblicazione: (2023)

OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
di: Yao, Yihang, et al.
Pubblicazione: (2024)

On Predictability of Reinforcement Learning Dynamics for Large Language Models
di: Cai, Yuchen, et al.
Pubblicazione: (2025)

Behavior Preference Regression for Offline Reinforcement Learning
di: Srinivasan, Padmanaba, et al.
Pubblicazione: (2025)

Offline Reinforcement Learning with Behavioral Supervisor Tuning
di: Srinivasan, Padmanaba, et al.
Pubblicazione: (2024)

Stabilizing Reinforcement Learning for Diffusion Language Models
di: Zhong, Jianyuan, et al.
Pubblicazione: (2026)

Behavior Backdoor for Deep Learning Models
di: Wang, Jiakai, et al.
Pubblicazione: (2024)

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
di: Zhou, Yang, et al.
Pubblicazione: (2026)

Learning to Inject: Automated Prompt Injection via Reinforcement Learning
di: Chen, Xin, et al.
Pubblicazione: (2026)

Offline Reinforcement Learning with Penalized Action Noise Injection
di: Oh, JunHyeok, et al.
Pubblicazione: (2025)

POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization
di: Wang, Ziqing, et al.
Pubblicazione: (2025)

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework
di: Han, William, et al.
Pubblicazione: (2025)

Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement Learning
di: Prasad, Romesh, et al.
Pubblicazione: (2024)

BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
di: Lin, Haohong, et al.
Pubblicazione: (2024)

EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
di: Zhang, Jesse, et al.
Pubblicazione: (2024)

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
di: Qian, Fuyuan, et al.
Pubblicazione: (2026)

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
di: Tang, Xiaohang, et al.
Pubblicazione: (2026)

SelfBC: Self Behavior Cloning for Offline Reinforcement Learning
di: Liu, Shirong, et al.
Pubblicazione: (2024)

From Observations to Events: Event-Aware World Model for Reinforcement Learning
di: Peng, Zhao-Han, et al.
Pubblicazione: (2026)

Behavior-Consistent Deep Reinforcement Learning
di: Hussing, Marcel, et al.
Pubblicazione: (2026)

Preparing Lessons for Progressive Training on Language Models
di: Pan, Yu, et al.
Pubblicazione: (2024)

Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
di: Zhang, Kongcheng, et al.
Pubblicazione: (2025)

Token-Efficient Leverage Learning in Large Language Models
di: Zeng, Yuanhao, et al.
Pubblicazione: (2024)

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
di: Yang, Tong, et al.
Pubblicazione: (2023)

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
di: Qian, Cheng, et al.
Pubblicazione: (2025)

UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts
di: Wang, Fu-Yun, et al.
Pubblicazione: (2025)

CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning
di: Zhao, Yanxiao, et al.
Pubblicazione: (2025)

Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning
di: Wu, Jiayun, et al.
Pubblicazione: (2025)

Fast and Distributed Equivariant Graph Neural Networks by Virtual Node Learning
di: Zhang, Yuelin, et al.
Pubblicazione: (2025)

Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainability
di: Aslami, Pooja, et al.
Pubblicazione: (2024)

Offline Model-Based Reinforcement Learning with Anti-Exploration
di: Srinivasan, Padmanaba, et al.
Pubblicazione: (2024)

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
di: Qian, Cheng, et al.
Pubblicazione: (2025)

Imitating Cost-Constrained Behaviors in Reinforcement Learning
di: Shao, Qian, et al.
Pubblicazione: (2024)

Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection
di: Peng, Yihang, et al.
Pubblicazione: (2026)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
di: Zhang, Tianle, et al.
Pubblicazione: (2024)