{"total":156,"rows":[{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"id":"2403.00564","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","created":"2024-03-01","cited_by_count":40,"area":"wm"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"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":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29,"area":"driving"},{"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":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","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":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2405.17784","title":"Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation","created":"2024-05-28","cited_by_count":20,"area":"deeprl"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"area":"deeprl"},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2105.04682","title":"Value Iteration in Continuous Actions, States and Time","created":"2021-05-10","cited_by_count":18,"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":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2205.00579","title":"Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learning","created":"2022-05-01","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":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2407.02466","title":"PWM: Policy Learning with Multi-Task World Models","created":"2024-07-02","cited_by_count":17,"area":"wm"},{"id":"2103.08255","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","created":"2021-03-15","cited_by_count":16,"area":null},{"id":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2010.12142","title":"Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning","created":"2020-10-23","cited_by_count":15,"area":"wm"},{"id":"2107.00306","title":"MHER: Model-based Hindsight Experience Replay","created":"2021-07-01","cited_by_count":15,"area":null},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14,"area":null},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14,"area":"offlinerl"},{"id":"2105.06350","title":"MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks","created":"2021-05-13","cited_by_count":13,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2111.08550","title":"On Effective Scheduling of Model-based Reinforcement Learning","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2305.07497","title":"Dynamically Conservative Self-Driving Planner for Long-Tail Cases","created":"2023-05-12","cited_by_count":13,"area":null},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"area":"deeprl"},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"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":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"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":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9,"area":"offlinerl"},{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2009.09593","title":"Dynamic Horizon Value Estimation for Model-based Reinforcement Learning","created":"2020-09-21","cited_by_count":8,"area":"wm"},{"id":"2102.11513","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","created":"2021-02-23","cited_by_count":8,"area":null},{"id":"2105.12189","title":"Robust Value Iteration for Continuous Control Tasks","created":"2021-05-25","cited_by_count":8,"area":null},{"id":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2110.01954","title":"Continuous-Time Fitted Value Iteration for Robust Policies","created":"2021-10-05","cited_by_count":6,"area":null},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2110.14993","title":"Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2206.01341","title":"Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control","created":"2022-06-02","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":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","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":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"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":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2111.05819","title":"Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2209.13126","title":"Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2404.00340","title":"Deep Reinforcement Learning in Autonomous Car Path Planning and Control: A Survey","created":"2024-03-30","cited_by_count":5,"area":"deeprl"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null},{"id":"2102.12962","title":"Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning","created":"2021-02-25","cited_by_count":4,"area":null},{"id":"2104.02981","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","created":"2021-04-07","cited_by_count":4,"area":"wm"},{"id":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2501.10116","title":"GAWM: Global-Aware World Model for Multi-Agent Reinforcement Learning","created":"2025-01-17","cited_by_count":4,"area":"wm"},{"id":"2507.11060","title":"Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing","created":"2025-07-15","cited_by_count":4,"area":"deeprl"},{"id":"2106.12194","title":"Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving","created":"2021-06-23","cited_by_count":3,"area":"driving"},{"id":"2203.14660","title":"Revisiting Model-based Value Expansion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2303.03787","title":"Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3,"area":"deeprl"},{"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":"2103.12999","title":"Discriminator Augmented Model-Based Reinforcement Learning","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2112.13937","title":"Multiagent Model-based Credit Assignment for Continuous Control","created":"2021-12-27","cited_by_count":2,"area":null},{"id":"2302.08139","title":"Model-Based Decentralized Policy Optimization","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2304.14698","title":"X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2308.03882","title":"Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations","created":"2023-08-07","cited_by_count":2,"area":"offlinerl"},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null}],"next_cursor":"100"}