{"total":98,"rows":[{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47,"area":"offlinerl"},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30,"area":null},{"id":"2203.05549","title":"Context is Everything: Implicit Identification for Dynamics Adaptation","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"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":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2311.03695","title":"Context Shift Reduction for Offline Meta-Reinforcement Learning","created":"2023-11-07","cited_by_count":18,"area":"offlinerl"},{"id":"2102.08291","title":"Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models","created":"2021-02-16","cited_by_count":17,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2410.11448","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","created":"2024-10-15","cited_by_count":17,"area":"wm"},{"id":"2403.10967","title":"Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization","created":"2024-03-16","cited_by_count":16,"area":"wm"},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2403.09859","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","created":"2024-03-14","cited_by_count":14,"area":"wm"},{"id":"2407.19523","title":"Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation","created":"2024-07-28","cited_by_count":13,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2102.06961","title":"PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators","created":"2021-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2310.15017","title":"Mind the Model, Not the Agent: The Primacy Bias in Model-based RL","created":"2023-10-23","cited_by_count":9,"area":"wm"},{"id":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2210.09337","title":"Robust Imitation of a Few Demonstrations with a Backwards Model","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2106.10365","title":"Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2204.02877","title":"PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2311.07558","title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","created":"2023-11-13","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":"2207.09071","title":"Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks","created":"2022-07-19","cited_by_count":5,"area":null},{"id":"2212.03857","title":"Phase2vec: Dynamical systems embedding with a physics-informed convolutional network","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2303.05092","title":"Task Aware Dreamer for Task Generalization in Reinforcement Learning","created":"2023-03-09","cited_by_count":5,"area":"wm"},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2310.03984","title":"AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems","created":"2023-10-06","cited_by_count":5,"area":null},{"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":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","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":"2508.20294","title":"Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization","created":"2025-08-27","cited_by_count":5,"area":"wm"},{"id":"2312.06518","title":"Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2407.18841","title":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","created":"2024-07-26","cited_by_count":4,"area":"deeprl"},{"id":"2411.01850","title":"ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations","created":"2024-11-04","cited_by_count":4,"area":null},{"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":"2509.13341","title":"Imagined Autocurricula","created":"2025-09-11","cited_by_count":4,"area":"wm"},{"id":"2203.00551","title":"Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty","created":"2022-03-01","cited_by_count":3,"area":null},{"id":"2207.14723","title":"Meta Reinforcement Learning with Successor Feature Based Context","created":"2022-07-29","cited_by_count":3,"area":null},{"id":"2211.12774","title":"Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning","created":"2022-11-23","cited_by_count":3,"area":"wm"},{"id":"2404.10942","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2405.19885","title":"Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning","created":"2024-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2502.11377","title":"PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.18471","title":"Action Flow Matching for Continual Robot Learning","created":"2025-04-25","cited_by_count":3,"area":"diffusion"},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2309.13508","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2406.08238","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","created":"2024-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2506.04399","title":"Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","created":"2025-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2511.11607","title":"Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"deeprl"},{"id":"2605.12178","title":"Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics","created":"2026-05-12","cited_by_count":2,"area":"wm"},{"id":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2203.06783","title":"Adaptive Model Predictive Control by Learning Classifiers","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2209.12029","title":"Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2210.04209","title":"Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning","created":"2022-10-09","cited_by_count":1,"area":null},{"id":"2303.11756","title":"Improving Deep Dynamics Models for Autonomous Vehicles with Multimodal Latent Mapping of Surfaces","created":"2023-03-21","cited_by_count":1,"area":"driving"},{"id":"2306.09742","title":"Meta Generative Flow Networks with Personalization for Task-Specific Adaptation","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2307.09206","title":"Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2406.04815","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","created":"2024-06-07","cited_by_count":1,"area":"deeprl"},{"id":"2407.06317","title":"Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation","created":"2024-07-08","cited_by_count":1,"area":"driving"},{"id":"2409.11452","title":"Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2505.19574","title":"Situationally-Aware Dynamics Learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.07006","title":"CARoL: Context-aware Adaptation for Robot Learning","created":"2025-06-08","cited_by_count":1,"area":"deeprl"},{"id":"2510.19357","title":"Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2512.23773","title":"FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading","created":"2025-12-29","cited_by_count":1,"area":"deeprl"},{"id":"2602.04037","title":"DADP: Domain Adaptive Diffusion Policy","created":"2026-02-03","cited_by_count":1,"area":"diffusion"},{"id":"2605.02699","title":"Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2608.19375","title":"Learning the Right Abstraction: Neural Reduced Dynamics for Complex Robot Control","created":"2026-08-19","cited_by_count":1,"area":"deeprl"},{"id":"2210.15515","title":"Meta-Reinforcement Learning Using Model Parameters","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2410.17186","title":"DyPNIPP: Predicting Environment Dynamics for RL-based Robust Informative Path Planning","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2503.06893","title":"Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning","created":"2025-03-10","cited_by_count":0,"area":"offlinerl"},{"id":"2505.16741","title":"Meta-reinforcement learning with minimum attention","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2506.06786","title":"Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2507.19437","title":"Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2510.05443","title":"AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Control","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2512.02417","title":"Vehicle Dynamics Embedded World Models for Autonomous Driving","created":"2025-12-02","cited_by_count":0,"area":"wm"},{"id":"2512.05172","title":"Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"mllm"},{"id":"2606.02280","title":"Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation","created":"2026-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2606.03521","title":"Post-Hoc Robustness for Model-Based Reinforcement Learning","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.13319","title":"Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.18910","title":"Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.18167","title":"Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning","created":"2026-09-16","cited_by_count":0,"area":"deeprl"},{"id":"2610.16763","title":"Relational Learning as World Modeling","created":"2026-10-12","cited_by_count":0,"area":"wm"}],"next_cursor":null}