Copertina

Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Shangzhe, Zhang, Xuchao, Bansal, Chetan, Zhang, Weitong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
di: Li, Shangzhe, et al.
Pubblicazione: (2025)

Imitation from Observations with Trajectory-Level Generative Embeddings
di: Qu, Yongtao, et al.
Pubblicazione: (2026)

CREAM: Consistency Regularized Self-Rewarding Language Models
di: Wang, Zhaoyang, et al.
Pubblicazione: (2024)

Reward-free World Models for Online Imitation Learning
di: Li, Shangzhe, et al.
Pubblicazione: (2024)

Learning Robust Reasoning through Guided Adversarial Self-Play
di: Li, Shuozhe, et al.
Pubblicazione: (2026)

Provable and Practical In-Context Policy Optimization for Self-Improvement
di: Yu, Tianrun, et al.
Pubblicazione: (2026)

Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
di: Li, Shangzhe, et al.
Pubblicazione: (2026)

AMPO: Active Multi-Preference Optimization for Self-play Preference Selection
di: Gupta, Taneesh, et al.
Pubblicazione: (2025)

Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
di: Li, Shangzhe, et al.
Pubblicazione: (2025)

Auto-Encoding Adversarial Imitation Learning
di: Zhang, Kaifeng, et al.
Pubblicazione: (2022)

Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance
di: Fang, Zheng, et al.
Pubblicazione: (2024)

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
di: Chen, Jiaqi, et al.
Pubblicazione: (2025)

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
di: Tan, Zhewen, et al.
Pubblicazione: (2026)

Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
di: Xu, Tian, et al.
Pubblicazione: (2026)

XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi
di: Zhou, Chenliang
Pubblicazione: (2024)

FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control
di: Ye, Yutong, et al.
Pubblicazione: (2025)

Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms
di: Li, Yichen, et al.
Pubblicazione: (2023)

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
di: Li, Gengsheng, et al.
Pubblicazione: (2026)

Latent Wasserstein Adversarial Imitation Learning
di: Yang, Siqi, et al.
Pubblicazione: (2026)

A Theoretical Framework for Self-Play Theorem Proving Algorithms
di: Chen, Thomas, et al.
Pubblicazione: (2026)

Self-Improving AI Agents through Self-Play
di: Chojecki, Przemyslaw
Pubblicazione: (2025)

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
di: Li, Na, et al.
Pubblicazione: (2025)

Scaling Self-Play with Self-Guidance
di: Bailey, Luke, et al.
Pubblicazione: (2026)

Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
di: Xu, Tian, et al.
Pubblicazione: (2022)

Self-evolved Imitation Learning in Simulated World
di: Ye, Yifan, et al.
Pubblicazione: (2025)

Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning
di: Li, Na, et al.
Pubblicazione: (2025)

Adversarial Imitation Learning via Boosting
di: Chang, Jonathan D., et al.
Pubblicazione: (2024)

Sample-efficient Adversarial Imitation Learning
di: Jung, Dahuin, et al.
Pubblicazione: (2023)

$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
di: Zhang, Yaocheng, et al.
Pubblicazione: (2026)

TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control
di: Zhuang, Zifeng, et al.
Pubblicazione: (2025)

Learning to Drive via Asymmetric Self-Play
di: Zhang, Chris, et al.
Pubblicazione: (2024)

COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
di: Wang, Lu, et al.
Pubblicazione: (2024)

Diffusion-Reward Adversarial Imitation Learning
di: Lai, Chun-Mao, et al.
Pubblicazione: (2024)

Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
di: Xu, Tian, et al.
Pubblicazione: (2024)

MILES: Making Imitation Learning Easy with Self-Supervision
di: Papagiannis, Georgios, et al.
Pubblicazione: (2024)

Dexterous Manipulation through Imitation Learning: A Survey
di: An, Shan, et al.
Pubblicazione: (2025)

From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning
di: Chaudhary, Gaurav, et al.
Pubblicazione: (2025)

How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning
di: Li, Haozhuo, et al.
Pubblicazione: (2025)

Match or Replay: Self Imitating Proximal Policy Optimization
di: Chaudhary, Gaurav, et al.
Pubblicazione: (2026)

REFA: Reference Free Alignment for multi-preference optimization
di: Gupta, Taneesh, et al.
Pubblicazione: (2024)