{"total":68,"rows":[{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154,"area":"offlinerl"},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2310.19807","title":"Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates","created":"2023-10-09","cited_by_count":21,"area":null},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2112.03850","title":"Policy Search for Model Predictive Control with Application to Agile Drone Flight","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2205.10218","title":"Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2304.12502","title":"Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach","created":"2023-04-25","cited_by_count":14,"area":"offlinerl"},{"id":"2310.06171","title":"Memory-Consistent Neural Networks for Imitation Learning","created":"2023-10-09","cited_by_count":14,"area":"offlinerl"},{"id":"2202.05244","title":"REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer","created":"2022-02-10","cited_by_count":13,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2401.13034","title":"Locality Sensitive Sparse Encoding for Learning World Models Online","created":"2024-01-23","cited_by_count":12,"area":"wm"},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2212.04359","title":"HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"1905.05637","title":"Randomized Adversarial Imitation Learning for Autonomous Driving","created":"2019-05-13","cited_by_count":6,"area":"offlinerl"},{"id":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2106.15775","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2111.15537","title":"Model-Free $\\mu$ Synthesis via Adversarial Reinforcement Learning","created":"2021-11-30","cited_by_count":5,"area":null},{"id":"2306.07098","title":"Efficiently Learning the Graph for Semi-supervised Learning","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2107.12254","title":"The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2008.09450","title":"Adversarial Imitation Learning via Random Search","created":"2020-08-21","cited_by_count":3,"area":"offlinerl"},{"id":"2105.06577","title":"Online Algorithms and Policies Using Adaptive and Machine Learning Approaches","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2405.03534","title":"Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2412.16561","title":"A learning-based approach to stochastic optimal control under reach-avoid constraint","created":"2024-12-21","cited_by_count":3,"area":"deeprl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2402.06912","title":"Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks","created":"2024-02-10","cited_by_count":2,"area":"deeprl"},{"id":"2102.07266","title":"Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2112.14710","title":"Parallelized and Randomized Adversarial Imitation Learning for Safety-Critical Self-Driving Vehicles","created":"2021-12-26","cited_by_count":1,"area":"driving"},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.13241","title":"State Combinatorial Generalization In Decision Making With Conditional Diffusion Models","created":"2025-01-22","cited_by_count":1,"area":"diffusion"},{"id":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2510.25063","title":"Control Synthesis with Reinforcement Learning: A Modeling Perspective","created":"2025-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2605.22305","title":"Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks","created":"2026-05-21","cited_by_count":1,"area":"deeprl"},{"id":"2108.02323","title":"Active Reinforcement Learning over MDPs","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2208.10583","title":"Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2303.16266","title":"On-line reinforcement learning for optimization of real-life energy trading strategy","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2310.14009","title":"One is More: Diverse Perspectives within a Single Network for Efficient DRL","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2311.00426","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2402.02904","title":"Replication of Impedance Identification Experiments on a Reinforcement-Learning-Controlled Digital Twin of Human Elbows","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2403.16767","title":"Policy Gradient-based Model Free Optimal LQG Control with a Probabilistic Risk Constraint","created":"2024-03-25","cited_by_count":0,"area":"deeprl"},{"id":"2409.13108","title":"Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning","created":"2024-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2601.04695","title":"Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning","created":"2026-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2604.20365","title":"Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.31310","title":"Model-free LQG Control with Chance Constraints","created":"2026-05-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}