{"list":"other","total":135,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","cited_by_count":178},{"id":"1811.11214","title":"Understanding the impact of entropy on policy optimization","created":"2018-11-27","cited_by_count":176},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1905.11614","title":"Uncertainty-based Continual Learning with Adaptive Regularization","created":"2019-05-28","cited_by_count":146},{"id":"1911.07676","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","created":"2019-11-18","cited_by_count":127},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101},{"id":"1911.02768","title":"Confidence Intervals for Policy Evaluation in Adaptive Experiments","created":"2019-11-07","cited_by_count":95},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92},{"id":"1810.03024","title":"Learning to Optimize under Non-Stationarity","created":"2018-10-06","cited_by_count":85},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77},{"id":"2003.01704","title":"Model Selection in Contextual Stochastic Bandit Problems","created":"2020-03-03","cited_by_count":71},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2002.03217","title":"Inference for Batched Bandits","created":"2020-02-08","cited_by_count":63},{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63},{"id":"2401.00820","title":"A Computational Framework for Behavioral Assessment of LLM Therapists","created":"2024-01-01","cited_by_count":62},{"id":"2506.22405","title":"Sequential Diagnosis with Language Models","created":"2025-06-27","cited_by_count":60},{"id":"2010.03110","title":"Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning","created":"2020-10-07","cited_by_count":53},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53},{"id":"2410.03017","title":"Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise","created":"2024-10-03","cited_by_count":50},{"id":"2012.13045","title":"Regret Bound Balancing and Elimination for Model Selection in Bandits and RL","created":"2020-12-24","cited_by_count":47},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45},{"id":"2503.06424","title":"Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues","created":"2025-03-09","cited_by_count":43},{"id":"1405.3316","title":"Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewards","created":"2014-05-13","cited_by_count":42},{"id":"1704.06880","title":"Misspecified Linear Bandits","created":"2017-04-23","cited_by_count":42},{"id":"1403.3741","title":"Near-optimal Reinforcement Learning in Factored MDPs","created":"2014-03-15","cited_by_count":41},{"id":"1507.00300","title":"Bootstrapped Thompson Sampling and Deep Exploration","created":"2015-07-01","cited_by_count":40},{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40},{"id":"1712.06695","title":"Accurate Inference for Adaptive Linear Models","created":"2017-12-18","cited_by_count":39},{"id":"1605.04070","title":"A Reinforcement Learning System to Encourage Physical Activity in Diabetes Patients","created":"2016-05-13","cited_by_count":38},{"id":"2307.04345","title":"Continual Learning as Computationally Constrained Reinforcement Learning","created":"2023-07-10","cited_by_count":37},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"2304.09853","title":"Bridging RL Theory and Practice with the Effective Horizon","created":"2023-04-19","cited_by_count":31},{"id":"2004.06230","title":"Power Constrained Bandits","created":"2020-04-13","cited_by_count":30},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29},{"id":"2201.06532","title":"A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits","created":"2022-01-17","cited_by_count":28},{"id":"1601.00237","title":"Assessing Time-Varying Causal Effect Moderation in Mobile Health","created":"2016-01-03","cited_by_count":27},{"id":"2406.06474","title":"Towards a Personal Health Large Language Model","created":"2024-06-10","cited_by_count":27},{"id":"2008.01571","title":"IntelligentPooling: Practical Thompson Sampling for mHealth","created":"2020-07-31","cited_by_count":24},{"id":"2010.15835","title":"Targeting for long-term outcomes","created":"2020-10-29","cited_by_count":23},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23},{"id":"2007.12000","title":"ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation","created":"2020-07-23","cited_by_count":22},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22},{"id":"2102.13240","title":"Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles","created":"2021-02-26","cited_by_count":21},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20},{"id":"2411.18822","title":"RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data","created":"2024-11-27","cited_by_count":20},{"id":"2208.12764","title":"Causal Bandits for Linear Structural Equation Models","created":"2022-08-26","cited_by_count":19},{"id":"2202.05100","title":"Adaptively Exploiting d-Separators with Causal Bandits","created":"2022-02-10","cited_by_count":18},{"id":"2208.07406","title":"Reward Design For An Online Reinforcement Learning Algorithm Supporting Oral Self-Care","created":"2022-08-15","cited_by_count":18},{"id":"2206.01995","title":"Combinatorial Causal Bandits","created":"2022-06-04","cited_by_count":16},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14},{"id":"2204.11165","title":"ReLoop: A Self-Correction Continual Learning Loop for Recommender Systems","created":"2022-04-24","cited_by_count":13},{"id":"2301.12366","title":"Smooth Non-Stationary Bandits","created":"2023-01-29","cited_by_count":13},{"id":"2202.07098","title":"Statistical Inference After Adaptive Sampling for Longitudinal Data","created":"2022-02-14","cited_by_count":12},{"id":"2402.10592","title":"Optimizing Adaptive Experiments: A Unified Approach to Regret Minimization and Best-Arm Identification","created":"2024-02-16","cited_by_count":12},{"id":"2306.02869","title":"Data-Driven Online Model Selection With Regret Guarantees","created":"2023-06-05","cited_by_count":11},{"id":"2309.07893","title":"Choosing a Proxy Metric from Past Experiments","created":"2023-09-14","cited_by_count":11},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11},{"id":"2409.02069","title":"A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial","created":"2024-09-03","cited_by_count":11}],"next_cursor":"100"}