{"total":159,"rows":[{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2110.14074","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","created":"2021-10-26","cited_by_count":54,"area":null},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2110.14771","title":"ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets","created":"2021-10-27","cited_by_count":36,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2203.14065","title":"Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture","created":"2022-03-26","cited_by_count":31,"area":null},{"id":"2103.11512","title":"Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study","created":"2021-03-21","cited_by_count":30,"area":null},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29,"area":null},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2306.13867","title":"Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems","created":"2023-06-24","cited_by_count":28,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"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":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"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":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2203.11203","title":"Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach","created":"2022-03-19","cited_by_count":17,"area":null},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2205.05569","title":"Delayed Reinforcement Learning by Imitation","created":"2022-05-11","cited_by_count":16,"area":null},{"id":"2108.11623","title":"Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian","created":"2021-08-26","cited_by_count":15,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","cited_by_count":14,"area":null},{"id":"2109.09478","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2206.07813","title":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2107.05686","title":"The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2403.06420","title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2205.14495","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2303.02160","title":"Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2110.01840","title":"Deep reinforcement learning for guidewire navigation in coronary artery phantom","created":"2021-10-05","cited_by_count":10,"area":null},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2201.11965","title":"Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2101.04750","title":"Linear Representation Meta-Reinforcement Learning for Instant Adaptation","created":"2021-01-12","cited_by_count":9,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2112.06127","title":"Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings","created":"2021-11-25","cited_by_count":9,"area":null},{"id":"2207.13131","title":"Semi-analytical Industrial Cooling System Model for Reinforcement Learning","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2210.05185","title":"Meta-Learning with Self-Improving Momentum Target","created":"2022-10-11","cited_by_count":9,"area":null},{"id":"2212.04914","title":"Information-Theoretic Safe Exploration with Gaussian Processes","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2301.13375","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","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":"2312.16174","title":"Industrial Internet of Things Intelligence Empowering Smart Manufacturing: A Literature Review","created":"2023-12-02","cited_by_count":8,"area":null},{"id":"2101.09650","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","created":"2021-01-24","cited_by_count":7,"area":null},{"id":"2105.05985","title":"An Open-Source Multi-Goal Reinforcement Learning Environment for Robotic Manipulation with Pybullet","created":"2021-05-12","cited_by_count":7,"area":null},{"id":"2207.02016","title":"Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization","created":"2022-07-05","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2406.10584","title":"Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models","created":"2024-06-15","cited_by_count":7,"area":null},{"id":"2207.01337","title":"Safe Reinforcement Learning via Confidence-Based Filters","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2202.13604","title":"Generalizable task representation learning from human demonstration videos: a geometric approach","created":"2022-02-28","cited_by_count":5,"area":null},{"id":"2101.05537","title":"Optimal Energy Shaping via Neural Approximators","created":"2021-01-14","cited_by_count":4,"area":null},{"id":"2203.06250","title":"Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2206.08781","title":"Reinforcement Learning for Economic Policy: A New Frontier?","created":"2022-06-16","cited_by_count":4,"area":null},{"id":"2209.12347","title":"Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2301.01148","title":"MERLIN: Multi-agent offline and transfer learning for occupant-centric energy flexible operation of grid-interactive communities using smart meter data and CityLearn","created":"2022-12-31","cited_by_count":4,"area":null},{"id":"2104.09650","title":"Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2108.01358","title":"Accelerating the Learning of TAMER with Counterfactual Explanations","created":"2021-08-03","cited_by_count":3,"area":null},{"id":"2109.07129","title":"What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2201.07016","title":"Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2204.13971","title":"Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2208.12136","title":"A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2210.02769","title":"Artificial virtuous agents in a multiagent tragedy of the commons","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2210.03649","title":"How to Enable Uncertainty Estimation in Proximal Policy Optimization","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2302.01595","title":"Deep Reinforcement Learning for Cyber System Defense under Dynamic Adversarial Uncertainties","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2303.07622","title":"RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback","created":"2023-03-14","cited_by_count":3,"area":null},{"id":"2304.01366","title":"Enabling A Network AI Gym for Autonomous Cyber Agents","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2306.02029","title":"Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2309.14989","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2310.18919","title":"Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"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":"2103.15370","title":"Robust Reinforcement Learning under model misspecification","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2107.04457","title":"Aligning an optical interferometer with beam divergence control and continuous action space","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2110.02566","title":"Adaptive control of a mechatronic system using constrained residual reinforcement learning","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2201.07092","title":"K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents","created":"2022-01-18","cited_by_count":2,"area":null},{"id":"2202.01534","title":"Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2202.04943","title":"Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2202.12872","title":"AutoFR: Automated Filter Rule Generation for Adblocking","created":"2022-02-25","cited_by_count":2,"area":null}],"next_cursor":"100"}