{"total":222,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2103.08624","title":"Autonomous Drone Racing with Deep Reinforcement Learning","created":"2021-03-15","cited_by_count":60,"area":null},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59,"area":null},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2102.07952","title":"A Survey of Machine Learning for Computer Architecture and Systems","created":"2021-02-16","cited_by_count":53,"area":null},{"id":"2201.07779","title":"Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation","created":"2022-01-19","cited_by_count":49,"area":null},{"id":"2503.24278","title":"AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World","created":"2025-03-31","cited_by_count":48,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2402.02500","title":"Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning","created":"2024-02-04","cited_by_count":45,"area":null},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2202.07141","title":"Machine Learning in Aerodynamic Shape Optimization","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36,"area":null},{"id":"2305.18446","title":"Trompt: Towards a Better Deep Neural Network for Tabular Data","created":"2023-05-29","cited_by_count":36,"area":null},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2210.12631","title":"LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation","created":"2022-10-23","cited_by_count":34,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33,"area":null},{"id":"2108.13035","title":"SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning","created":"2021-08-30","cited_by_count":31,"area":null},{"id":"2202.10688","title":"Graph Lifelong Learning: A Survey","created":"2022-02-22","cited_by_count":30,"area":null},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30,"area":null},{"id":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2107.04271","title":"FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning","created":"2021-07-09","cited_by_count":26,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2305.17473","title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2111.03941","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","created":"2021-11-06","cited_by_count":23,"area":null},{"id":"2201.12569","title":"Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes","created":"2022-01-29","cited_by_count":23,"area":null},{"id":"2305.12972","title":"VanillaNet: the Power of Minimalism in Deep Learning","created":"2023-05-22","cited_by_count":23,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2111.11743","title":"Independent Learning in Stochastic Games","created":"2021-11-23","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":"2409.18382","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models","created":"2024-09-27","cited_by_count":22,"area":null},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2305.04866","title":"Causal Policy Gradient for Whole-Body Mobile Manipulation","created":"2023-05-04","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":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2110.14457","title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching","created":"2021-10-27","cited_by_count":19,"area":null},{"id":"2102.11055","title":"Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization","created":"2021-02-22","cited_by_count":18,"area":null},{"id":"2103.07932","title":"Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems","created":"2021-03-14","cited_by_count":18,"area":null},{"id":"2205.06311","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","created":"2022-05-12","cited_by_count":18,"area":null},{"id":"2209.14076","title":"Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems","created":"2022-09-28","cited_by_count":18,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2202.12180","title":"Quantum Deep Reinforcement Learning for Robot Navigation Tasks","created":"2022-02-24","cited_by_count":16,"area":null},{"id":"2409.04882","title":"Learning to Open and Traverse Doors with a Legged Manipulator","created":"2024-09-07","cited_by_count":16,"area":null},{"id":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2308.01194","title":"Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation","created":"2023-08-02","cited_by_count":14,"area":null},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"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":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2204.02041","title":"Automating Reinforcement Learning with Example-based Resets","created":"2022-04-05","cited_by_count":12,"area":null},{"id":"2401.10490","title":"Generalization Error Guaranteed Auto-Encoder-Based Nonlinear Model Reduction for Operator Learning","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2509.15733","title":"GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation","created":"2025-09-19","cited_by_count":12,"area":null},{"id":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2208.00843","title":"Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards","created":"2022-08-01","cited_by_count":11,"area":null},{"id":"2304.08743","title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2102.07716","title":"How RL Agents Behave When Their Actions Are Modified","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2103.01391","title":"Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2108.13976","title":"WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU","created":"2021-08-31","cited_by_count":10,"area":null},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2201.09765","title":"Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning","created":"2022-01-24","cited_by_count":10,"area":null},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2212.06111","title":"Where To Start? Transferring Simple Skills to Complex Environments","created":"2022-12-12","cited_by_count":9,"area":null},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2103.05981","title":"Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme","created":"2021-03-10","cited_by_count":8,"area":null},{"id":"2106.03129","title":"3D UAV Trajectory and Data Collection Optimisation via Deep Reinforcement Learning","created":"2021-06-06","cited_by_count":8,"area":null},{"id":"2201.08504","title":"Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2212.11681","title":"Variational Quantum Soft Actor-Critic for Robotic Arm Control","created":"2022-12-20","cited_by_count":8,"area":null},{"id":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2305.10411","title":"Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2310.20178","title":"Learning to Discover Skills through Guidance","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2108.07887","title":"Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay","created":"2021-08-17","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2104.13617","title":"End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning","created":"2021-04-28","cited_by_count":6,"area":null},{"id":"2105.08846","title":"Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education","created":"2021-05-18","cited_by_count":6,"area":null},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2205.11913","title":"Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2206.10716","title":"Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2211.11281","title":"Intelligent Computing: The Latest Advances, Challenges and Future","created":"2022-11-21","cited_by_count":6,"area":null}],"next_cursor":"100"}