{"total":96,"rows":[{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512,"area":"wm"},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2311.00168","title":"The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback","created":"2023-10-31","cited_by_count":42,"area":"alignment"},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2603.22078","title":"Do World Action Models Generalize Better than VLAs? A Robustness Study","created":"2026-03-23","cited_by_count":36,"area":"wm"},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32,"area":null},{"id":"2202.08494","title":"Learning continuous models for continuous physics","created":"2022-02-17","cited_by_count":28,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24,"area":null},{"id":"2105.10049","title":"Learning Modular Robot Control Policies","created":"2021-05-20","cited_by_count":22,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2110.01894","title":"Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models","created":"2021-10-05","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2204.13319","title":"Control-Aware Prediction Objectives for Autonomous Driving","created":"2022-04-28","cited_by_count":18,"area":"driving"},{"id":"2109.08815","title":"Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation","created":"2021-09-18","cited_by_count":17,"area":null},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2407.02466","title":"PWM: Policy Learning with Multi-Task World Models","created":"2024-07-02","cited_by_count":17,"area":"wm"},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","cited_by_count":14,"area":null},{"id":"2210.09256","title":"On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2202.00916","title":"Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health","created":"2022-02-02","cited_by_count":12,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2312.05250","title":"TaskMet: Task-Driven Metric Learning for Model Learning","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2512.09929","title":"Closing the Train-Test Gap in World Models for Gradient-Based Planning","created":"2025-12-10","cited_by_count":11,"area":"wm"},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2606.15032","title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","created":"2026-06-13","cited_by_count":10,"area":"wm"},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9,"area":"offlinerl"},{"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":"2211.13937","title":"Operator Splitting Value Iteration","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2402.05421","title":"DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning","created":"2024-02-08","cited_by_count":6,"area":"offlinerl"},{"id":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"id":"2510.00931","title":"Making, not Taking, the Best of N","created":"2025-10-01","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":"2410.09972","title":"Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions","created":"2024-10-13","cited_by_count":5,"area":"deeprl"},{"id":"2205.10677","title":"Risk-Driven Design of Perception Systems","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2606.01626","title":"IMWM: Intuition Models Complement World Models for Latent Planning","created":"2026-06-01","cited_by_count":4,"area":"wm"},{"id":"2106.03279","title":"Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning","created":"2021-06-06","cited_by_count":3,"area":null},{"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":"2407.10967","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","created":"2024-07-15","cited_by_count":3,"area":"offlinerl"},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2607.14169","title":"When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models","created":"2026-07-15","cited_by_count":3,"area":"wm"},{"id":"2608.01926","title":"ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching","created":"2026-08-03","cited_by_count":3,"area":"wm"},{"id":"2608.12939","title":"Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency","created":"2026-08-13","cited_by_count":3,"area":"wm"},{"id":"2608.29998","title":"The Intervention Gap in Latent World Models","created":"2026-08-30","cited_by_count":3,"area":"wm"},{"id":"2103.12999","title":"Discriminator Augmented Model-Based Reinforcement Learning","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2602.10044","title":"Optimistic World Models: Efficient Exploration in Model-Based Deep Reinforcement Learning","created":"2026-02-10","cited_by_count":2,"area":"wm"},{"id":"2607.01736","title":"Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander","created":"2026-07-02","cited_by_count":2,"area":"wm"},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2204.06895","title":"Gradient boosting for convex cone predict and optimize problems","created":"2022-04-14","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","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":"2411.07484","title":"DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients","created":"2024-11-12","cited_by_count":1,"area":"deeprl"},{"id":"2510.17709","title":"Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimality","created":"2025-10-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2607.18589","title":"Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States","created":"2026-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2607.20152","title":"Active Inference as a Convex Markov Decision Process","created":"2026-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2608.17956","title":"An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models","created":"2026-08-18","cited_by_count":1,"area":"wm"},{"id":"2209.04854","title":"Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning","created":"2022-09-11","cited_by_count":0,"area":null},{"id":"2304.00252","title":"Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning","created":"2023-04-01","cited_by_count":0,"area":null},{"id":"2312.16184","title":"Dynamic Knowledge Injection for AIXI Agents","created":"2023-12-18","cited_by_count":0,"area":null},{"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":"2412.06486","title":"SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation","created":"2024-12-09","cited_by_count":0,"area":"wm"},{"id":"2507.13491","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","created":"2025-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2511.06252","title":"MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios","created":"2025-11-09","cited_by_count":0,"area":"wm"},{"id":"2604.08944","title":"Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2606.07399","title":"Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.14585","title":"Sensitivity Shaping for Latent Modeling","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.06640","title":"What a World Model Represents Is Three Questions","created":"2026-07-07","cited_by_count":0,"area":"wm"},{"id":"2608.28541","title":"An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models","created":"2026-08-28","cited_by_count":0,"area":"wm"},{"id":"2609.21474","title":"MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.33030","title":"What Must a World Model Distinguish for Planning?","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.35400","title":"Structural Alignment for Reliable Industrial AI: Bridging Physical Reality, Data, Models, and Human Intent","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36645","title":"Where Predictive Supervision Goes Shapes What VLA Policies Learn","created":"2026-09-29","cited_by_count":0,"area":"vla"},{"id":"2609.39235","title":"The Planning Limits of Latent World Models","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.00921","title":"In CEM, a World Model Is Also a Proposal Mechanism","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.03065","title":"Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04494","title":"DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents","created":"2026-10-03","cited_by_count":0,"area":"wm"},{"id":"2610.05550","title":"When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models","created":"2026-10-04","cited_by_count":0,"area":"wm"},{"id":"2610.08033","title":"Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA","created":"2026-10-06","cited_by_count":0,"area":"wm"},{"id":"2610.14368","title":"History, Adaptation, and Hidden Gain: Two Prospective Tests of Learned Predictive Control in a Synthetic Neural Population","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14413","title":"Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16763","title":"Relational Learning as World Modeling","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.19375","title":"One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}