{"total":94,"rows":[{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2202.00728","title":"Physical Design using Differentiable Learned Simulators","created":"2022-02-01","cited_by_count":37,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","cited_by_count":29,"area":null},{"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":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2202.08004","title":"Deep Koopman Operator with Control for Nonlinear Systems","created":"2022-02-16","cited_by_count":25,"area":null},{"id":"2105.03363","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","created":"2021-05-07","cited_by_count":24,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2105.10049","title":"Learning Modular Robot Control Policies","created":"2021-05-20","cited_by_count":22,"area":null},{"id":"2210.15185","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","created":"2022-10-27","cited_by_count":22,"area":null},{"id":"2109.08522","title":"Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires","created":"2021-09-16","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17,"area":null},{"id":"2111.14693","title":"SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14,"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":"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":"2301.12538","title":"On Approximating the Dynamic Response of Synchronous Generators via Operator Learning: A Step Towards Building Deep Operator-based Power Grid Simulators","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2210.11579","title":"Model-based Lifelong Reinforcement Learning with Bayesian Exploration","created":"2022-10-20","cited_by_count":12,"area":null},{"id":"2107.11587","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","created":"2021-07-24","cited_by_count":11,"area":null},{"id":"2204.11464","title":"Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods","created":"2022-04-25","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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2111.08067","title":"ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control","created":"2021-11-15","cited_by_count":8,"area":null},{"id":"2401.13836","title":"Machine learning for industrial sensing and control: A survey and practical perspective","created":"2024-01-24","cited_by_count":8,"area":null},{"id":"2206.01162","title":"Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning","created":"2022-06-02","cited_by_count":7,"area":null},{"id":"2208.11838","title":"Learning Task Automata for Reinforcement Learning using Hidden Markov Models","created":"2022-08-25","cited_by_count":7,"area":null},{"id":"2212.09510","title":"Near-optimal Policy Identification in Active Reinforcement Learning","created":"2022-12-19","cited_by_count":7,"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":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2201.00354","title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference","created":"2022-01-02","cited_by_count":6,"area":null},{"id":"2302.07160","title":"Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2505.17966","title":"Is Single-View Mesh Reconstruction Ready for Robotics?","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2206.08442","title":"A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2212.08235","title":"A Simple Decentralized Cross-Entropy Method","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2301.12802","title":"Planning Multiple Epidemic Interventions with Reinforcement Learning","created":"2023-01-30","cited_by_count":5,"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":"2112.06018","title":"Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control","created":"2021-12-11","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2110.13079","title":"Which Model to Trust: Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms for Continuous Control Tasks","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2203.00551","title":"Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty","created":"2022-03-01","cited_by_count":3,"area":null},{"id":"2212.01343","title":"CT-DQN: Control-Tutored Deep Reinforcement Learning","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2310.13576","title":"Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2103.12999","title":"Discriminator Augmented Model-Based Reinforcement Learning","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2103.14407","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2104.04174","title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning","created":"2021-04-09","cited_by_count":2,"area":null},{"id":"2205.10044","title":"Towards biologically plausible Dreaming and Planning in recurrent spiking networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2208.02434","title":"Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2301.03933","title":"Hint assisted reinforcement learning: an application in radio astronomy","created":"2023-01-10","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":"2305.17552","title":"Online Nonstochastic Model-Free Reinforcement Learning","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2411.07832","title":"Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2503.13438","title":"Deep Belief Markov Models for POMDP Inference","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2111.08108","title":"Physics-informed neural networks via stochastic Hamiltonian dynamics learning","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2206.09743","title":"Guided Safe Shooting: model based reinforcement learning with safety constraints","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2209.01693","title":"Variational Inference for Model-Free and Model-Based Reinforcement Learning","created":"2022-09-04","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":"2407.12964","title":"Learning Long-Horizon Predictions for Quadrotor Dynamics","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2005.08844","title":"Advanced Policies: A First-Principles Path from Policy Gradient to Q-Learning","created":"2020-05-18","cited_by_count":0,"area":null},{"id":"2109.09390","title":"Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representations","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2204.01925","title":"Online No-regret Model-Based Meta RL for Personalized Navigation","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2211.12610","title":"Efficient Exploration using Model-Based Quality-Diversity with Gradients","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2212.02715","title":"Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2309.11089","title":"Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2312.05547","title":"Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following","created":"2023-12-09","cited_by_count":0,"area":null},{"id":"2505.18201","title":"Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2602.12520","title":"Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}