{"total":21,"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":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2409.14216","title":"R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models","created":"2024-09-21","cited_by_count":10,"area":"wm"},{"id":"2508.18507","title":"Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies","created":"2025-08-25","cited_by_count":7,"area":"wm"},{"id":"2506.08441","title":"Time-Aware World Model for Adaptive Prediction and Control","created":"2025-06-10","cited_by_count":4,"area":"wm"},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2406.09976","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","created":"2024-06-14","cited_by_count":3,"area":"wm"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2403.01962","title":"An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement","created":"2024-03-04","cited_by_count":2,"area":"wm"},{"id":"2509.24116","title":"Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems","created":"2025-09-28","cited_by_count":2,"area":"wm"},{"id":"2605.14382","title":"Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation","created":"2026-05-14","cited_by_count":2,"area":"wm"},{"id":"2401.11660","title":"Differentiable Tree Search Network","created":"2024-01-22","cited_by_count":1,"area":"wm"},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2509.15915","title":"Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds","created":"2025-09-19","cited_by_count":1,"area":"wm"},{"id":"2510.21232","title":"How Hard is it to Confuse a World Model?","created":"2025-10-24","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":"2607.10630","title":"World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning","created":"2026-07-12","cited_by_count":1,"area":"wm"},{"id":"2110.13241","title":"Multitask Adaptation by Retrospective Exploration with Learned World Models","created":"2021-10-25","cited_by_count":0,"area":"wm"},{"id":"2610.14936","title":"CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance","created":"2026-10-10","cited_by_count":0,"area":"wm"},{"id":"2610.15368","title":"ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs","created":"2026-10-11","cited_by_count":0,"area":"wm"}],"next_cursor":null}