{"total":54,"rows":[{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2401.10529","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","created":"2024-01-19","cited_by_count":94,"area":"lr"},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"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":"2410.05364","title":"Diffusion Model Predictive Control","created":"2024-10-07","cited_by_count":36,"area":"diffusion"},{"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":"2202.08494","title":"Learning continuous models for continuous physics","created":"2022-02-17","cited_by_count":28,"area":null},{"id":"2405.06263","title":"Learning Latent Dynamic Robust Representations for World Models","created":"2024-05-10","cited_by_count":21,"area":"wm"},{"id":"2302.01244","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2107.01825","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","created":"2021-07-05","cited_by_count":18,"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":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2405.17031","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":10,"area":"offlinerl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"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":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2108.11645","title":"Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control","created":"2021-08-26","cited_by_count":6,"area":null},{"id":"2209.05530","title":"Model-based Reinforcement Learning with Multi-step Plan Value Estimation","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2405.17234","title":"Benchmarking General-Purpose In-Context Learning","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2211.11027","title":"Safe Reinforcement Learning using Data-Driven Predictive Control","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2504.01766","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2409.09513","title":"Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens","created":"2024-09-14","cited_by_count":4,"area":"offlinerl"},{"id":"2509.23846","title":"Adversarial Diffusion for Robust Reinforcement Learning","created":"2025-09-28","cited_by_count":4,"area":"diffusion"},{"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":"2410.21497","title":"Denoising Diffusion Planner: Learning Complex Paths from Low-Quality Demonstrations","created":"2024-10-28","cited_by_count":2,"area":"diffusion"},{"id":"2508.06096","title":"Bounding Distributional Shifts in World Modeling through Novelty Detection","created":"2025-08-08","cited_by_count":2,"area":"wm"},{"id":"2112.05218","title":"Learning Generalizable Behavior via Visual Rewrite Rules","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2310.05672","title":"Multi-timestep models for Model-based Reinforcement Learning","created":"2023-10-09","cited_by_count":1,"area":"offlinerl"},{"id":"2401.12822","title":"Deep Learning Based Simulators for the Phosphorus Removal Process Control in Wastewater Treatment via Deep Reinforcement Learning Algorithms","created":"2024-01-23","cited_by_count":1,"area":"deeprl"},{"id":"2407.12964","title":"Learning Long-Horizon Predictions for Quadrotor Dynamics","created":"2024-07-17","cited_by_count":1,"area":null},{"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":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"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":"2605.04568","title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.17548","title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"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":"2606.22860","title":"HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning","created":"2026-06-22","cited_by_count":1,"area":"vla"},{"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":"2108.01295","title":"MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2112.02817","title":"ED2: Environment Dynamics Decomposition World Models for Continuous Control","created":"2021-12-06","cited_by_count":0,"area":"wm"},{"id":"2206.00316","title":"Model Generation with Provable Coverability for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":0,"area":"offlinerl"},{"id":"2511.06816","title":"Controllable Flow Matching for Online Reinforcement Learning","created":"2025-11-10","cited_by_count":0,"area":"diffusion"},{"id":"2607.17560","title":"Reinforcement Learning: From Algorithms To Foundation Models","created":"2026-07-20","cited_by_count":0,"area":"wm"},{"id":"2608.21554","title":"Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts","created":"2026-08-21","cited_by_count":0,"area":"deeprl"},{"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}