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. Heterogeneous AAV Logistics Task Allocation: A Reinforcement Learning Enhanced Overlapping Coalition Formation Game Approach

    May 26, 2026Yuze Zhou, Jingliang Sun, Junzhi Li +3Reinforcement LearningTransformer-Based RL

    Beijing Institute of Technology, Beijing 100081, China · Key Laboratory of Dynamics and Control of Flight Vehicle, Ministry of Education, Beijing 100081, China · Beijing Institute of Technology Chongqing Innovation Center, Chongqing, 401121, China +1

  2. Identifiable Token Correspondence for World Models

    May 15, 2026Youngin Kim, Ray Sun, Inho Kim +2World Model LearningTransformer-Based RL

    Interdisciplinary Program in Artificial Intelligence, Seoul National University · Department of Computer Science and Engineering, Seoul National University · KRAFTON

  3. One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning

    May 10, 2026Bowen He, Juncheng Dong, Lin Lin +1Reinforcement LearningTransformer

    Duke University, Durham, U.S.A.

  4. ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network

    May 10, 2026Qian Chen, Junqiao Zhao, Hongtu Zhou +4Reinforcement LearningTransformer-Based RL

    Tongji University

  5. Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning

    May 8, 2026Zixuan Xie, Xinyu Liu, Claire Chen +3Reinforcement LearningTransformer-Based RL

    University of Virginia · California Institute of Technology · Purdue University

  6. Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought

    May 8, 2026Zixuan Xie, Xinyu Liu, Rohan Chandra +1Reinforcement LearningTransformer

    University of Virginia

  7. Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer

    May 7, 2026Yongyi Wang, Hanyu Liu, Lingfeng Li +6Efficient Transformer InferenceReinforcement Learning

    School of Computer Science Peking University Beijing, China 100871

  8. Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement

    May 7, 2026Haodong Liang, Lifeng LaiReinforcement LearningTransformer-Based RL

    Department of Electrical and Computer Engineering, University of California, Davis

  9. Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus

    Apr 15, 2026Zijian Zhao, Jing Gao, Sen LiCooperative MARLMulti-Agent Reinforcement Learning

    1The Hong Kong University of Science and Technology · 2The Hong Kong Polytechnic University · 3The Hong Kong University of Science and Technology (Guangzhou)

  10. MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning

    Apr 7, 2026Maria Nesterova, Mikhail Kolosov, Anton Andreychuk +6Multi-Agent Reinforcement LearningTransformer-Based RL

    AXXX & MIRAI, Moscow, Russia · MIRAI, Moscow, Russia · AXXX, Moscow, Russia +2

  11. Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

    Apr 6, 2026Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin +11In-Context RLTransformer-Based RL

    AXXX, Applied AI Institute · AXXX, Innopolis University · AXXX, HSE +7

  12. Meta-Adaptive Beam Search Planning for Transformer-Based Reinforcement Learning Control of UAVs with Overhead Manipulators under Flight Disturbances

    Mar 27, 2026Hazim Alzorgan, Sayed Pedram Haeri Boroujeni, Abolfazl RaziAerial ManipulationRobot Trajectory Tracking

    School of Computing, Clemson University, Clemson, SC 29632, USA

  13. Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems

    Mar 27, 2026Pascal Henrich, Jonas Sievers, Maximilian Beichter +3Policy DistillationTransformer-Based RL

    Karlsruhe Institute of Technology, Karlsruhe, Germany

  14. A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem

    Mar 25, 2026Faezeh Ardali, Mwembezi A. Nyelele, Gerald M. KnappCombinatorial OptimizationNeural Combinatorial Optimization

    Louisiana State University, Baton Rouge, LA, USA · University of Minnesota Duluth, Duluth, MN, USA

  15. STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning

    Mar 12, 2026Jiwon Jeon, Myungsik Cho, Youngchul SungOffline MARLTransformer-Based RL

    School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon 34141, Republic of Korea

  16. Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification

    Mar 11, 2026Hang Yu, Huidong Liu, Qingchen Zhang +5Offline RLSafe RL

    School of Engineering, University of Warwick, Coventry, UK · School of Computer Science, Chongqing University, China · School of Computer Science and Technology, Hainan University, China +1

  17. RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States

    Mar 7, 2026Xiangjie Xiao, Cong Zhang, Wen Song +1Flexible Job Shop SchedulingJob Shop Scheduling

    School of Computing and Information Systems, Singapore Management University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore · Institute of Marine Science and Technology, Shandong University, China

  18. When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift

    Mar 4, 2026Kevin Vogt-Lowell, Theodoros Tsiligkaridis, Rodney Lafuente-Mercado +4Robust RLPartially Observable RL

    MIT Lincoln Laboratory · Harvard · MIT

  19. IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning

    Mar 4, 2026Yihao Qin, Yuanfei Wang, Hang Zhou +3Offline RLTransformer-Based RL

    The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Peking University Beijing, China

  20. Next Embedding Prediction Makes World Models Stronger

    Mar 3, 2026George Bredis, Nikita Balagansky, Daniil Gavrilov +1Model-Based RLPartially Observable RL

    T-Tech.

  21. MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning

    Feb 27, 2026Chenxing Lin, Xinhui Gao, Haipeng Zhang +7Offline RLTransformer-Based RL

    Fujian Key Laboratory of Urban Intelligent Sensing and Computing, School of Informatics, Xiamen University (XMU), China · Key Laboratory of Multimedia Trusted Perception and Efficient Computing, XMU, China · Hong Kong University of Science and Technology +2

  22. TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs

    Feb 20, 2026Rong Fu, Yibo Meng, Zeyu Zhang +4Real-Time SchedulingTransformer-Based RL

    Independent Researcher

  23. Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

    Oct 21, 2025Brady Bhalla, Honglu Fan, Nancy Chen +1Transformer InterpretabilityRepresentation Learning

    California Institute of Technology · Pasadena, CA 91125 · Google DeepMind +3