{"total":29,"rows":[{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42,"area":"wm"},{"id":"2310.16029","title":"Finetuning Offline World Models in the Real World","created":"2023-10-24","cited_by_count":41,"area":"wm"},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41,"area":"wm"},{"id":"2402.03570","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","created":"2024-02-05","cited_by_count":31,"area":"wm"},{"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":"2504.16680","title":"Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots","created":"2025-04-23","cited_by_count":17,"area":"wm"},{"id":"2410.00564","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","created":"2024-10-01","cited_by_count":14,"area":"wm"},{"id":"2206.04384","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":12,"area":"wm"},{"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":"2405.19878","title":"Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models","created":"2024-05-30","cited_by_count":8,"area":"wm"},{"id":"2507.13340","title":"Latent Policy Steering with Embodiment-Agnostic Pretrained World Models","created":"2025-07-17","cited_by_count":8,"area":"wm"},{"id":"2305.15260","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","created":"2023-05-24","cited_by_count":7,"area":"wm"},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2509.13341","title":"Imagined Autocurricula","created":"2025-09-11","cited_by_count":4,"area":"wm"},{"id":"2407.04942","title":"FOSP: Fine-tuning Offline Safe Policy through World Models","created":"2024-07-06","cited_by_count":3,"area":"wm"},{"id":"2505.07257","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","created":"2025-05-12","cited_by_count":2,"area":"wm"},{"id":"2509.19538","title":"DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions","created":"2025-09-23","cited_by_count":2,"area":"wm"},{"id":"2607.07196","title":"Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators","created":"2026-07-08","cited_by_count":2,"area":"wm"},{"id":"2608.17163","title":"Q-Learning With World Models","created":"2026-08-17","cited_by_count":2,"area":"wm"},{"id":"2603.22430","title":"Inference Time Policy Optimization for Offline RL with Differentiable World Models","created":"2026-03-23","cited_by_count":1,"area":"wm"},{"id":"2306.03360","title":"Model-Based Reinforcement Learning with Multi-Task Offline Pretraining","created":"2023-06-06","cited_by_count":0,"area":"wm"},{"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":"2506.22112","title":"Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems","created":"2025-06-27","cited_by_count":0,"area":"wm"},{"id":"2607.14180","title":"RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences","created":"2026-07-15","cited_by_count":0,"area":"wm"},{"id":"2609.13845","title":"LePlanner: An Iterative Amortized Controller For World Models","created":"2026-09-12","cited_by_count":0,"area":"wm"},{"id":"2610.14727","title":"MHWA: Multi-timescale Hierarchical World-Action Model","created":"2026-10-10","cited_by_count":0,"area":"wm"}],"next_cursor":null}