{"total":63,"rows":[{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2410.09536","title":"TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning","created":"2024-10-12","cited_by_count":19,"area":"deeprl"},{"id":"2406.00079","title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","created":"2024-05-31","cited_by_count":18,"area":"ssm"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2310.06171","title":"Memory-Consistent Neural Networks for Imitation Learning","created":"2023-10-09","cited_by_count":14,"area":"offlinerl"},{"id":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12,"area":"wm"},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2506.15635","title":"FindingDory: A Benchmark to Evaluate Memory in Embodied Agents","created":"2025-06-18","cited_by_count":12,"area":"mllm"},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"id":"2405.15384","title":"Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate","created":"2024-05-24","cited_by_count":10,"area":"deeprl"},{"id":"2409.01449","title":"Real-Time Recurrent Learning using Trace Units in Reinforcement Learning","created":"2024-09-02","cited_by_count":10,"area":"deeprl"},{"id":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","cited_by_count":9,"area":"deeprl"},{"id":"2409.15703","title":"Agent-state based policies in POMDPs: Beyond belief-state MDPs","created":"2024-09-24","cited_by_count":9,"area":"deeprl"},{"id":"2410.10132","title":"Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning","created":"2024-10-14","cited_by_count":9,"area":"deeprl"},{"id":"2510.19732","title":"Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning","created":"2025-10-22","cited_by_count":9,"area":"deeprl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2410.02751","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","created":"2024-10-03","cited_by_count":7,"area":"deeprl"},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2406.01361","title":"Learning to Play Atari in a World of Tokens","created":"2024-06-03","cited_by_count":6,"area":"wm"},{"id":"2408.01402","title":"Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer","created":"2024-08-02","cited_by_count":6,"area":"offlinerl"},{"id":"2510.07151","title":"ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2409.16824","title":"Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability","created":"2024-09-25","cited_by_count":5,"area":"deeprl"},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2402.07102","title":"An Empirical Study on the Power of Future Prediction in Partially Observable Environments","created":"2024-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2606.10507","title":"HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning","created":"2026-06-09","cited_by_count":3,"area":"agents"},{"id":"2406.17168","title":"Reinforcement Learning via Auxiliary Task Distillation","created":"2024-06-24","cited_by_count":2,"area":"deeprl"},{"id":"2505.15040","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","created":"2025-05-21","cited_by_count":2,"area":"ssm"},{"id":"2604.05808","title":"Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2405.03878","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning","created":"2024-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2412.15427","title":"AdaCred: Adaptive Causal Decision Transformers with Feature Crediting","created":"2024-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.05084","title":"Recurrent State Encoders for Efficient Neural Combinatorial Optimization","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2601.15086","title":"Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2602.05679","title":"Perception-Based Beliefs for POMDPs with Visual Observations","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2505.18083","title":"What Do You Need for Compositional Generalization in Diffusion Planning?","created":"2025-05-23","cited_by_count":0,"area":"offlinerl"},{"id":"2510.13367","title":"A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2511.06946","title":"Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning","created":"2025-11-10","cited_by_count":0,"area":"wm"},{"id":"2602.19837","title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2602.20643","title":"TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.16509","title":"Learning-Guided Sparsification of Dynamic Graphs in Robotic Exploration","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.17431","title":"MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2608.05111","title":"Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.19804","title":"ADAPT: Physics-Aware Diffusion-based World Models for Adaptive Predictive Transferable HVAC Control","created":"2026-08-20","cited_by_count":0,"area":"wm"},{"id":"2609.25757","title":"Minimal Recurrent Behavioral Memory for Imitation under Partial Observability","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33169","title":"When Does Backpropagating Through Policy Memory Matter? Physical Credit, Optimizer Updates, and Observability","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2609.38598","title":"Reinforcement Learning with Complex (valued) Memories","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.00592","title":"ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.00982","title":"Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies","created":"2026-10-01","cited_by_count":0,"area":"vla"},{"id":"2610.01513","title":"Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2610.13197","title":"Does Learning Recurrent Networks Matter in Partially Observable RL?","created":"2026-10-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}