{"total":108,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123,"area":"lr"},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2505.11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","created":"2025-05-16","cited_by_count":43,"area":"deeprl"},{"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":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2401.14534","title":"Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQR","created":"2024-01-25","cited_by_count":17,"area":"deeprl"},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"area":"offlinerl"},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2309.14970","title":"Recurrent Hypernetworks are Surprisingly Strong in Meta-RL","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2406.01575","title":"Contextual Bilevel Reinforcement Learning for Incentive Alignment","created":"2024-06-03","cited_by_count":14,"area":"alignment"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2602.10503","title":"Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning","created":"2026-02-11","cited_by_count":13,"area":"vla"},{"id":"2305.15695","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","created":"2023-05-25","cited_by_count":12,"area":null},{"id":"2504.19139","title":"Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments","created":"2025-04-27","cited_by_count":12,"area":null},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2504.14520","title":"Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey","created":"2025-04-20","cited_by_count":10,"area":"lr"},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2402.06402","title":"Hierarchical Transformers are Efficient Meta-Reinforcement Learners","created":"2024-02-09","cited_by_count":8,"area":"deeprl"},{"id":"2410.03737","title":"Meta Reinforcement Learning Approach for Adaptive Resource Optimization in O-RAN","created":"2024-09-30","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2408.03093","title":"Certifiably Robust Policies for Uncertain Parametric Environments","created":"2024-08-06","cited_by_count":7,"area":null},{"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":"2405.04491","title":"TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characters","created":"2024-05-07","cited_by_count":6,"area":"driving"},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"},{"id":"2404.09521","title":"Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning","created":"2024-04-15","cited_by_count":5,"area":"deeprl"},{"id":"2405.02299","title":"Deep Reinforcement Learning for Modelling Protein Complexes","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2502.16667","title":"MetaSym: A Symplectic Meta-learning Framework for Physical Intelligence","created":"2025-02-23","cited_by_count":5,"area":null},{"id":"2506.01299","title":"Scalable In-Context Q-Learning","created":"2025-06-02","cited_by_count":5,"area":"wm"},{"id":"2307.02276","title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2503.01885","title":"Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4,"area":"offlinerl"},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2410.08355","title":"Metalic: Meta-Learning In-Context with Protein Language Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2411.04466","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","created":"2024-11-07","cited_by_count":3,"area":"deeprl"},{"id":"2502.00983","title":"CausalCOMRL: Context-Based Offline Meta-Reinforcement Learning with Causal Representation","created":"2025-02-03","cited_by_count":3,"area":"offlinerl"},{"id":"2505.11175","title":"Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"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":"2305.12216","title":"On First-Order Meta-Reinforcement Learning with Moreau Envelopes","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2307.11357","title":"Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2403.03020","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","created":"2024-03-05","cited_by_count":2,"area":"deeprl"},{"id":"2403.17364","title":"A Moreau Envelope Approach for LQR Meta-Policy Estimation","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2407.00495","title":"A Bayesian Solution To The Imitation Gap","created":"2024-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2410.09728","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","created":"2024-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2503.01062","title":"Offline RLAIF: Piloting VLM Feedback for RL via SFO","created":"2025-03-02","cited_by_count":2,"area":"mllm"},{"id":"2503.23650","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective","created":"2025-03-31","cited_by_count":2,"area":"driving"},{"id":"2506.06832","title":"Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2602.07335","title":"Meta-Reinforcement Learning for Robust and Non-greedy Control Barrier Functions in Spacecraft Proximity Operations","created":"2026-02-07","cited_by_count":2,"area":"deeprl"},{"id":"2603.05621","title":"RACAS: Controlling Diverse Robots With a Single Agentic System","created":"2026-03-05","cited_by_count":2,"area":"agents"},{"id":"2603.22479","title":"Cognitive Training for Language Models: Towards General Capabilities via Cross-Entropy Games","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2605.24423","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","created":"2026-05-23","cited_by_count":2,"area":"deeprl"},{"id":"2606.15306","title":"LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure","created":"2026-06-13","cited_by_count":2,"area":"agents"},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2312.05465","title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2312.06695","title":"Evolving Reservoirs for Meta Reinforcement Learning","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2405.11397","title":"Preparing for Black Swans: The Antifragility Imperative for Machine Learning","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2406.12359","title":"Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents","created":"2024-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2407.17502","title":"MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation","created":"2024-07-05","cited_by_count":1,"area":"deeprl"},{"id":"2407.18913","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","created":"2024-07-26","cited_by_count":1,"area":"deeprl"},{"id":"2502.01492","title":"Develop AI Agents for System Engineering in Factorio","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.07911","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","created":"2025-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"id":"2601.21845","title":"Constrained Meta Reinforcement Learning with Provable Test-Time Safety","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2607.11906","title":"In-Context Reinforcement Learning under Non-Stationarity: A Survey","created":"2026-07-01","cited_by_count":1,"area":"deeprl"},{"id":"2306.15909","title":"RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2406.14047","title":"Constrained Meta Agnostic Reinforcement Learning","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2406.19561","title":"Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning","created":"2024-06-27","cited_by_count":0,"area":"deeprl"},{"id":"2407.00744","title":"Disentangled Representations for Causal Cognition","created":"2024-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2408.15800","title":"Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2502.10792","title":"Tackling the Zero-Shot Reinforcement Learning Loss Directly","created":"2025-02-15","cited_by_count":0,"area":"deeprl"},{"id":"2505.22442","title":"Fully Offline Reinforcement Learning","created":"2025-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2506.06891","title":"Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2507.07348","title":"Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts","created":"2025-07-10","cited_by_count":0,"area":"deeprl"},{"id":"2510.23448","title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","created":"2025-10-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.17564","title":"JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.02935","title":"Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"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}],"next_cursor":"100"}