Cover Image

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Haodong, Lai, Lifeng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transformers Handle Endogeneity in In-Context Linear Regression
by: Liang, Haodong, et al.
Published: (2024)

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
by: Lu, Ziqing, et al.
Published: (2025)

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

Agentic Transformers Provably Learn to Search via Reinforcement Learning
by: Yang, Tong, et al.
Published: (2026)

Towards Monotonic Improvement in In-Context Reinforcement Learning
by: Zhang, Wenhao, et al.
Published: (2025)

Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
by: Liang, Haodong, et al.
Published: (2025)

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
by: Anisimov, Maksim, et al.
Published: (2026)

Blending Imitation and Reinforcement Learning for Robust Policy Improvement
by: Liu, Xuefeng, et al.
Published: (2023)

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
by: Goodall, Alexander W., et al.
Published: (2025)

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
by: Lin, Licong, et al.
Published: (2023)

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
by: Liang, Hao, et al.
Published: (2022)

One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
by: Li, Zihao, et al.
Published: (2024)

Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
by: Xiao, Minheng, et al.
Published: (2024)

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
by: Yue, Bo, et al.
Published: (2024)

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

Heuristic Transformer: Belief Augmented In-Context Reinforcement Learning
by: Dippel, Oliver, et al.
Published: (2025)

The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations
by: Lehmann, Matthias
Published: (2024)

Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces
by: Kar, Avik, et al.
Published: (2024)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
by: Banerjee, Arko, et al.
Published: (2024)

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
by: Zhang, Hongming, et al.
Published: (2023)

Random Policy Enables In-Context Reinforcement Learning within Trust Horizons
by: Chen, Weiqin, et al.
Published: (2024)

Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
by: Walter, Tim, et al.
Published: (2025)

Neural Paging: Learning Context Management Policies for Turing-Complete Agents
by: Chen, Liang, et al.
Published: (2026)

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning
by: Luo, Zhi, et al.
Published: (2024)

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
by: Huang, Sili, et al.
Published: (2024)

Towards Provable Log Density Policy Gradient
by: Katdare, Pulkit, et al.
Published: (2024)

Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
by: Dong, Juncheng, et al.
Published: (2026)

Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
by: Zhao, Weiye, et al.
Published: (2024)

Provable Multi-Party Reinforcement Learning with Diverse Human Feedback
by: Zhong, Huiying, et al.
Published: (2024)

Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes
by: Vora, Kevin, et al.
Published: (2025)

Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning
by: Li, Yanjie, et al.
Published: (2024)

Provable Reward-Agnostic Preference-Based Reinforcement Learning
by: Zhan, Wenhao, et al.
Published: (2023)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
by: Bu, Dake, et al.
Published: (2025)

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
by: Yu, Xudong, et al.
Published: (2024)

Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization
by: Hao, Ruijie, et al.
Published: (2026)

HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback
by: Li, Ang, et al.
Published: (2024)

Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development
by: Xu, Changfu, et al.
Published: (2025)

The Formalism-Implementation Gap in Reinforcement Learning Research
by: Castro, Pablo Samuel
Published: (2025)

Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
by: Peng, Nianli, et al.
Published: (2023)

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
by: Cho, Taehyun, et al.
Published: (2024)