{"total":62,"rows":[{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"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":"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":"2511.11478","title":"Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective","created":"2025-11-14","cited_by_count":20,"area":"vla"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2309.17207","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","created":"2023-09-29","cited_by_count":16,"area":null},{"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":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2306.11488","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","created":"2023-06-20","cited_by_count":11,"area":"wm"},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"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":"2303.03284","title":"The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2310.04128","title":"Reinforcement Learning with Fast and Forgetful Memory","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","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":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2312.11935","title":"Parameterized Decision-making with Multi-modal Perception for Autonomous Driving","created":"2023-12-19","cited_by_count":7,"area":"driving"},{"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":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"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":"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":"2412.13093","title":"Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks","created":"2024-12-17","cited_by_count":4,"area":"deeprl"},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2507.00257","title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","created":"2025-06-30","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":"2604.00904","title":"Fatigue-Aware Learning to Defer via Constrained Optimisation","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2505.13837","title":"Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2606.02775","title":"AURA: Action-Gated Memory for Robot Policies at Constant VRAM","created":"2026-06-01","cited_by_count":2,"area":"inference"},{"id":"2307.11704","title":"JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning","created":"2023-07-21","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":"2605.24709","title":"Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning","created":"2026-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2605.31261","title":"Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2306.11483","title":"Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2504.06983","title":"Free Random Projection for In-Context Reinforcement Learning","created":"2025-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2512.06204","title":"Quantifying Memory Use in Reinforcement Learning with Temporal Range","created":"2025-12-05","cited_by_count":0,"area":"deeprl"},{"id":"2604.09671","title":"Belief-State RWKV for Reinforcement Learning under Partial Observability","created":"2026-04-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.26627","title":"Breaking the Epistemic Trap: Active Perception Under Compound Uncertainty","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2605.27946","title":"Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.02686","title":"ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.26040","title":"Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance","created":"2026-07-28","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":"2609.38598","title":"Reinforcement Learning with Complex (valued) Memories","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.39082","title":"Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39151","title":"Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.00592","title":"ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.01527","title":"Exact Distinguishability in Non-Markovian Decision Processes","created":"2026-10-01","cited_by_count":0,"area":null},{"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}