{"total":18,"rows":[{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"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":"2405.06263","title":"Learning Latent Dynamic Robust Representations for World Models","created":"2024-05-10","cited_by_count":21,"area":"wm"},{"id":"2411.05619","title":"WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making","created":"2024-11-08","cited_by_count":9,"area":"wm"},{"id":"2602.14351","title":"WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control","created":"2026-02-15","cited_by_count":3,"area":"wm"},{"id":"2508.06096","title":"Bounding Distributional Shifts in World Modeling through Novelty Detection","created":"2025-08-08","cited_by_count":2,"area":"wm"},{"id":"2509.05735","title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","created":"2025-09-06","cited_by_count":1,"area":"wm"},{"id":"2602.02799","title":"Joint Learning of Hierarchical Neural Options and Abstract World Model","created":"2026-02-02","cited_by_count":1,"area":"wm"},{"id":"2604.09035","title":"Advantage-Guided Diffusion for Model-Based Reinforcement Learning","created":"2026-04-10","cited_by_count":1,"area":"wm"},{"id":"2606.05558","title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents","created":"2026-06-04","cited_by_count":1,"area":"wm"},{"id":"2608.07420","title":"Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction","created":"2026-08-07","cited_by_count":1,"area":"wm"},{"id":"2608.17959","title":"Towards Zero-Shot Task Transfer with Neurosymbolic World Models","created":"2026-08-18","cited_by_count":1,"area":"wm"},{"id":"2112.02817","title":"ED2: Environment Dynamics Decomposition World Models for Continuous Control","created":"2021-12-06","cited_by_count":0,"area":"wm"},{"id":"2607.17560","title":"Reinforcement Learning: From Algorithms To Foundation Models","created":"2026-07-20","cited_by_count":0,"area":"wm"},{"id":"2609.33595","title":"Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning","created":"2026-09-27","cited_by_count":0,"area":"wm"},{"id":"2610.06637","title":"Long-Horizon Textual World Modeling through Structured Reasoning","created":"2026-10-05","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}