{"total":111,"rows":[{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2403.14520","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","created":"2024-03-21","cited_by_count":97,"area":"mllm"},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74,"area":"ssm"},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"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":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"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":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"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":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2307.02064","title":"Facing Off World Model Backbones: RNNs, Transformers, and S4","created":"2023-07-05","cited_by_count":31,"area":"wm"},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2305.11598","title":"Introspective Tips: Large Language Model for In-Context Decision Making","created":"2023-05-19","cited_by_count":28,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"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":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"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":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2311.05241","title":"When Meta-Learning Meets Online and Continual Learning: A Survey","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2404.09293","title":"A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion","created":"2024-04-14","cited_by_count":11,"area":"ssm"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2502.10178","title":"From Markov to Laplace: How Mamba In-Context Learns Markov Chains","created":"2025-02-14","cited_by_count":11,"area":"ssm"},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"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":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2502.20168","title":"Accelerating Model-Based Reinforcement Learning with State-Space World Models","created":"2025-02-27","cited_by_count":10,"area":"wm"},{"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":"2505.12171","title":"Learning to Dissipate Energy in Oscillatory State-Space Models","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2310.05167","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","created":"2023-10-08","cited_by_count":8,"area":"wm"},{"id":"2405.20881","title":"S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusion","created":"2024-05-31","cited_by_count":8,"area":"ssm"},{"id":"2406.00392","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","created":"2024-06-01","cited_by_count":8,"area":"deeprl"},{"id":"2410.14086","title":"In-context learning and Occam's razor","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"id":"2407.06136","title":"Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning","created":"2024-07-08","cited_by_count":7,"area":"ssm"},{"id":"2408.15740","title":"MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanisms","created":"2024-08-28","cited_by_count":7,"area":"ssm"},{"id":"2504.08020","title":"Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"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":"2403.17978","title":"Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection","created":"2024-03-23","cited_by_count":6,"area":null},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2410.10905","title":"Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale","created":"2024-10-13","cited_by_count":6,"area":"deeprl"},{"id":"2503.08751","title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","created":"2025-03-11","cited_by_count":6,"area":"wm"},{"id":"2505.23686","title":"ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork","created":"2025-05-29","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":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"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":"2506.01299","title":"Scalable In-Context Q-Learning","created":"2025-06-02","cited_by_count":5,"area":"wm"},{"id":"2509.19658","title":"RoboSSM: Scalable In-context Imitation Learning via State-Space Models","created":"2025-09-24","cited_by_count":5,"area":"offlinerl"},{"id":"2510.20668","title":"From Masks to Worlds: A Hitchhiker's Guide to World Models","created":"2025-10-23","cited_by_count":5,"area":"wm"},{"id":"2410.08893","title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","created":"2024-10-11","cited_by_count":4,"area":"wm"},{"id":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2407.09375","title":"HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2502.00466","title":"EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling","created":"2025-02-01","cited_by_count":3,"area":"wm"},{"id":"2502.01330","title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2506.14448","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2506.21037","title":"RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2509.18389","title":"Towards Provable Emergence of In-Context Reinforcement Learning","created":"2025-09-22","cited_by_count":3,"area":"deeprl"},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","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":"2602.21712","title":"Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling","created":"2026-02-25","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":"2408.02661","title":"Context-aware Mamba-based Reinforcement Learning for social robot navigation","created":"2024-08-05","cited_by_count":2,"area":"ssm"},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2506.13892","title":"Scaling Algorithm Distillation for Continuous Control with Mamba","created":"2025-06-16","cited_by_count":2,"area":"ssm"},{"id":"2507.06204","title":"Differential Mamba","created":"2025-07-08","cited_by_count":2,"area":"ssm"},{"id":"2605.05951","title":"HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning","created":"2026-05-07","cited_by_count":2,"area":"wm"},{"id":"2403.10696","title":"On the low-shot transferability of [V]-Mamba","created":"2024-03-15","cited_by_count":1,"area":"ssm"},{"id":"2410.22165","title":"EconoJax: A Fast & Scalable Economic Simulation in Jax","created":"2024-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2503.18201","title":"Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization","created":"2025-03-23","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":"2602.18857","title":"VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning","created":"2026-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2605.26035","title":"Length Generalization with Log-Depth Recurrent Units","created":"2026-05-25","cited_by_count":1,"area":null},{"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":"2609.13716","title":"JaxAHT: A JAX-Based Library for Ad Hoc Teamwork","created":"2026-09-12","cited_by_count":1,"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":"2505.11153","title":"Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2506.06891","title":"Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2510.08226","title":"UAMDP: Uncertainty-Aware Markov Decision Process for Risk-Constrained Reinforcement Learning from Probabilistic Forecasts","created":"2025-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2511.16191","title":"CausalMamba: Interpretable State Space Modeling for Temporal Rumor Causality","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.06204","title":"Quantifying Memory Use in Reinforcement Learning with Temporal Range","created":"2025-12-05","cited_by_count":0,"area":"deeprl"},{"id":"2512.18146","title":"On Swarm Leader Identification using Probing Policies","created":"2025-12-20","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}