{"total":199,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350,"area":"lr"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"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":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"area":"offlinerl"},{"id":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"area":"offlinerl"},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65,"area":"offlinerl"},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2407.00993","title":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents","created":"2024-07-01","cited_by_count":56,"area":"agents"},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"id":"2405.19690","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":43,"area":"diffusion"},{"id":"2310.06343","title":"Boosting Continuous Control with Consistency Policy","created":"2023-10-10","cited_by_count":38,"area":"diffusion"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2103.09575","title":"Regularized Behavior Value Estimation","created":"2021-03-17","cited_by_count":32,"area":"offlinerl"},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31,"area":"offlinerl"},{"id":"2301.04462","title":"An Analysis of Quantile Temporal-Difference Learning","created":"2023-01-11","cited_by_count":31,"area":null},{"id":"2302.05793","title":"Distributional GFlowNets with Quantile Flows","created":"2023-02-11","cited_by_count":28,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2103.04909","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","created":"2021-03-08","cited_by_count":26,"area":"wm"},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2310.05858","title":"Distributional Soft Actor-Critic with Three Refinements","created":"2023-10-09","cited_by_count":25,"area":null},{"id":"2412.01034","title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","created":"2024-12-02","cited_by_count":25,"area":"vla"},{"id":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24,"area":null},{"id":"2110.15335","title":"Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning","created":"2021-10-28","cited_by_count":24,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22,"area":null},{"id":"2412.13211","title":"ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks","created":"2024-12-09","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":"2507.23675","title":"One-Step Flow Policy Mirror Descent","created":"2025-07-31","cited_by_count":21,"area":"diffusion"},{"id":"2601.03044","title":"SOP: A Scalable Online Post-Training System for Vision-Language-Action Models","created":"2026-01-06","cited_by_count":21,"area":"vla"},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2108.13680","title":"Learning Practically Feasible Policies for Online 3D Bin Packing","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2401.17173","title":"Zero-Shot Reinforcement Learning via Function Encoders","created":"2024-01-30","cited_by_count":18,"area":"deeprl"},{"id":"2105.10266","title":"Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving","created":"2021-05-21","cited_by_count":17,"area":"driving"},{"id":"2101.08477","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2105.11366","title":"GMAC: A Distributional Perspective on Actor-Critic Framework","created":"2021-05-24","cited_by_count":16,"area":null},{"id":"2205.11051","title":"Flow-based Recurrent Belief State Learning for POMDPs","created":"2022-05-23","cited_by_count":16,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","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":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2505.00663","title":"Wasserstein Policy Optimization","created":"2025-05-01","cited_by_count":13,"area":"deeprl"},{"id":"2212.02094","title":"Learning Physically Realizable Skills for Online Packing of General 3D Shapes","created":"2022-12-05","cited_by_count":12,"area":null},{"id":"2310.20266","title":"Beyond Average Return in Markov Decision Processes","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2102.13446","title":"Safe Distributional Reinforcement Learning","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2103.08233","title":"Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning","created":"2021-03-15","cited_by_count":10,"area":null},{"id":"2112.06061","title":"OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion","created":"2021-12-11","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2311.01642","title":"Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula","created":"2023-11-03","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":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10,"area":"driving"},{"id":"2407.04315","title":"Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning","created":"2024-07-05","cited_by_count":10,"area":"deeprl"},{"id":"2207.13131","title":"Semi-analytical Industrial Cooling System Model for Reinforcement Learning","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","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":"2111.10898","title":"Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning","created":"2021-11-21","cited_by_count":8,"area":null},{"id":"2210.11698","title":"Learning Robust Dynamics through Variational Sparse Gating","created":"2022-10-21","cited_by_count":8,"area":"wm"},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2509.23087","title":"Unleashing Flow Policies with Distributional Critics","created":"2025-09-27","cited_by_count":8,"area":"offlinerl"},{"id":"2110.00704","title":"OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation","created":"2021-10-02","cited_by_count":7,"area":null},{"id":"2202.00088","title":"Reinforcement Learning with Heterogeneous Data: Estimation and Inference","created":"2022-01-31","cited_by_count":7,"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":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2204.10256","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","created":"2022-04-21","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2102.12103","title":"FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism","created":"2021-02-24","cited_by_count":5,"area":null},{"id":"2106.08918","title":"Towards Automatic Actor-Critic Solutions to Continuous Control","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2110.09904","title":"Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space","created":"2021-10-19","cited_by_count":5,"area":null},{"id":"2111.12600","title":"Learning State Representations via Retracing in Reinforcement Learning","created":"2021-11-24","cited_by_count":5,"area":null},{"id":"2112.12740","title":"Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2210.11262","title":"RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2405.02576","title":"CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics","created":"2024-05-04","cited_by_count":5,"area":"deeprl"}],"next_cursor":"100"}