Transformer-Based RL

RL: Reinforcement Learning

Ask about this topic

Overview

Transformer-based reinforcement learning studies how attention-based models can use past observations, actions, and rewards to make decisions over time. Common approaches include Decision Transformers that model trajectories, world models that predict future states, and policies trained with offline or online reinforcement learning; transformers are also used for multi-agent coordination and safety-aware control. The field is extending these methods to long-horizon tasks, diverse environments, and in-context learning, while theory increasingly examines when attention can implement familiar updates such as temporal-difference learning. Key challenges include generalizing beyond training data, managing limited context and computation, and ensuring that strong benchmark performance translates to reliable behavior in deployment.

Latest papers

CardsList

53 papers12 papers in the last four weeks, up 71% on the four weeks before. 0.1% of all new papers.

  1. DT-JEPA: Learning to Predict Future Representations for Decision-Making

    Oct 23, 2026Changxu Ni, Yiyang Ni, Jun Li +4Transformer-Based RLSelf-Supervised RL

    Southeast University · Jiangsu Second Normal University · The University of Hong Kong +1

  2. Is In-Context Reinforcement Learning A Posterior Sampler? An Empirical Study

    Oct 20, 2026Weiqin Chen, Xinlong Du, Gesualdo Scutari +1In-Context RLTransformer-Based RL

    Edwardson School of Industrial Engineering, Purdue University West Lafayette, IN 47907, USA

  3. Reframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations

    Oct 20, 2026Cedric Derstroff, Jannis Blüml, Janosch Moos +4Reinforcement LearningRepresentation Learning for RL

    The Hessian Center for Artificial Intelligence (hessian.AI) · Technische Universität Darmstadt · Centre for Cognitive Science +1

  4. Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory

    Oct 19, 2026Jiawen Wang, Cheng Xue, Peng Zhang +1Reinforcement LearningIn-Context RL

    The Australian National University

  5. Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?

    Oct 16, 2026Shiguang Wu, Yaqing Wang, Quanming YaoIn-Context LearningIn-Context RL

    Tsinghua University · Beijing Institute of Mathematical Sciences and Applications

  6. Provable Transformer Context Compression for In-Context Reinforcement Learning

    Oct 14, 2026Yajie Zhao, Yingjun Mo, Zhiyong Wang +3In-Context RLIn-Context Learning

    Southern University of Science and Technology · University of Electronic Science and Technology of China · Harbin Institute of Technology

  7. From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning

    Oct 13, 2026Yingjun Mo, Yajie Zhao, Fang KongIn-Context RLTransformer-Based RL

    Southern University of Science and Technology (SUSTech) · University of Electronic Science and Technology of China (UESTC)

  8. Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers

    Oct 6, 2026Naoki Nishikawa, Taiji SuzukiReward ModelingTransformer-Based RL

    The University of Tokyo, RIKEN AIP

  9. Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer Policies

    Oct 2, 2026Amit Thakur, Mukesh SinghalMulti-Agent SystemsMulti-Agent Reinforcement Learning

    University of California, Merced

  10. Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning

    Oct 1, 2026Jude Waide, Robert LieckReinforcement LearningTransformer-Based RL

    Department of Computer Science, University of Durham, Durham, United Kingdom.

  11. Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning

    Sep 29, 2026T. Konstantin Rusch, Tim Seyde, Jared Boyer +2Reinforcement LearningPolicy Learning

    ELLIS Institute Tübingen & Max Planck Institute for Intelligent Systems & Tübingen AI Center & Liquid AI · Liquid AI · CSAIL, MIT +1

  12. Q-learning Penalized Transformer for Safe Offline Reinforcement Learning

    Sep 28, 2026Shengchao Hu, Peng Wang, Jifeng Hu +5Reinforcement LearningTransformer-Based RL

    Shanghai Jiao Tong University, China · Shenzhen Campus of Sun Yat-sen University, China · Jilin University, China +1

  13. Trust Guided Decision Transformer

    Sep 25, 2026Chainesh Gautam, Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi +3Transformer-Based RLDecision Transformer

    International Institute of Information Technology Bangalore · IBM Research Bangalore

  14. PolicyAttention: Softmax Attention Implements Policy Mirror Descent for Closed-Loop Control

    Sep 24, 2026Yuhe Sui, Yingzhi Tang, Shufang ChenPolicy LearningPolicy Optimization

    Quantitative Research Society, Singapore · Nanyang Technological University, Singapore · The Chinese University of Hong Kong, Shenzhen, China +1

  15. From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning

    Sep 24, 2026Yichen Lin, Xuyuan Xiong, Xue Wang +3In-Context RLTransformer-Based RL

    Shanghai Jiao Tong University, Shanghai, China · Alibaba Group · School of Management, University at Buffalo, Buffalo, NY, USA

  16. Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning

    Sep 20, 2026Suman Banerjee, Hiroyasu TsukamotoReinforcement LearningTransformer-Based RL

    Department of Aerospace Engineering, The Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA

  17. Runtime-Incremental Transformer for Reinforcement-Learning-Based Adaptive Control

    Sep 11, 2026Giansalvo Cirrincione, Adriano FagioliniRobotic ControlAdaptive Control

    Laboratoire LTI, Université de Picardie Jules Verne, Amiens, France · MIRPALab, Department of Engineering, University of Palermo, 90128 Palermo, Italy

  18. Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent Transformers

    Sep 7, 2026Sarvesh PatilRobotic ManipulationMulti-Robot Coordination

    Carnegie Mellon University, The Robotics Institute Pittsburgh, PA, United States

  19. Human-Human & Human-Robot Interaction Transformer (H2INT) for Robot Navigation in Dense and Uncertain Crowds

    Sep 4, 2026Ao Shen, Kaixi Chen, Shiwei Liu +2Robot NavigationSocial Robot Navigation

    School of Automation, Beijing Institute of Technology, Beijing 100081, China · State Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing 100081, China

  20. Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformers

    Aug 24, 2026Hossein Abdi, Satya Prakash Dash, Mingfei SunRL ControlTransformer-Based RL

    Department of Computer Science, The University of Manchester, Manchester, UK

  21. LLMs are Few-Shot Decision-Makers: Generalized Context-Aware Microgrid Frequency Control through Prompt Decision Transformer

    Aug 22, 2026Xu Yang, Chenhui Lin, Haotian Liu +3Power SystemsTransformer-Based RL

    State Key Laboratory of Power Systems, Department of Electrical Engineering, Tsinghua University, Beijing 100084, China

  22. Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking

    Aug 13, 2026Faezeh Ardali, Gerald M. KnappVehicle RoutingRL for Combinatorial Optimization

    Department of Industrial Engineering, Louisiana State University, Baton Rouge, LA, USA

  23. Learning-Based Collaborative MEC for LLM Inference with Soft-Deadline Awareness via Transformer-Enhanced PPO

    Aug 3, 2026Ngoc Hung Nguyen, Bjorn LandfeldtReinforcement LearningTransformer-Based RL

    Department of Electrical and Information Technology, Lund University, P.O. Box 117, Lund 22100, Sweden

  24. Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

    Jul 1, 2026Zijian Zhang, Rizhen Hu, Athanasios Glentis +4RL for Language ModelsFine-Tuning

    University of Minnesota · Peking University · Amazon

  25. Revealing Safety-Critical Scenarios for UTM via Transformer

    Jun 30, 2026Huaze Tang, Bill Zeng, Chao Wang +3Reinforcement LearningIntelligent Transportation Systems

    Tsinghua University · Meituan

  26. Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

    Jun 23, 2026Thibaut KulakReinforcement LearningTransformer

    NeoInstinct SA

  27. Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies

    Jun 6, 2026Ashkan Ansarifard, Matteo Mancanelli, Elena Umili +1Reinforcement LearningTransformer-Based RL

    Sapienza University of Rome · University of Rome La Sapienza, Rome, Italy

  28. Agentic Transformers Provably Learn to Search via Reinforcement Learning

    May 29, 2026Tong Yang, Yu Huang, Yingbin Liang +1Policy GradientAgentic RL

    Department of Electrical and Computer Engineering, Carnegie Mellon University · Department of Statistics and Data Science, Wharton School, University of Pennsylvania · Department of Electrical and Computer Engineering, The Ohio State University +1

  29. ESPO: Early-Stopping Proximal Policy Optimization

    May 28, 2026Zihang Li, Rui Zhou, Yingcheng Shi +8LLM ReasoningReinforcement Learning

    1Tongyi Lab , Alibaba Group · 2Peking University

  30. Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

    May 26, 2026Nguyen Cong Luong, Shaohan Feng, Nguyen Duc Hai +10Reinforcement LearningTransformer-Based RL

    Faculty of Computer Science, Phenikaa University, Hanoi 12116, Vietnam · School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou 310018, China · Faculty of Artificial Intelligence and Data Science, Phenikaa University, Duong Noi, Hanoi 12116, Vietnam +4