{"list":"other","total":60,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1704.00445","title":"On Kernelized Multi-armed Bandits","created":"2017-04-03","cited_by_count":352},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1807.02582","title":"Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences","created":"2018-07-06","cited_by_count":192},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1710.01688","title":"On the Sample Complexity of the Linear Quadratic Regulator","created":"2017-10-04","cited_by_count":159},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115},{"id":"2008.06389","title":"Sample-efficient Cross-Entropy Method for Real-time Planning","created":"2020-08-14","cited_by_count":95},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"2006.10277","title":"Active Learning for Nonlinear System Identification with Guarantees","created":"2020-06-18","cited_by_count":80},{"id":"1902.06223","title":"Learning Linear-Quadratic Regulators Efficiently with only $\\sqrt{T}$ Regret","created":"2019-02-17","cited_by_count":70},{"id":"1909.03539","title":"Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity","created":"2019-09-08","cited_by_count":70},{"id":"1705.10257","title":"Boltzmann Exploration Done Right","created":"2017-05-29","cited_by_count":69},{"id":"1310.1863","title":"Empowerment -- an Introduction","created":"2013-10-07","cited_by_count":68},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62},{"id":"2007.01891","title":"A Unifying View of Optimism in Episodic Reinforcement Learning","created":"2020-07-03","cited_by_count":52},{"id":"1605.04070","title":"A Reinforcement Learning System to Encourage Physical Activity in Diabetes Patients","created":"2016-05-13","cited_by_count":38},{"id":"2112.09605","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","created":"2021-12-17","cited_by_count":33},{"id":"2312.16730","title":"Foundations of Reinforcement Learning and Interactive Decision Making","created":"2023-12-27","cited_by_count":33},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30},{"id":"1905.05150","title":"AMZ Driverless: The Full Autonomous Racing System","created":"2019-05-13","cited_by_count":29},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28},{"id":"1911.09946","title":"Actively Learning Gaussian Process Dynamics","created":"2019-11-22","cited_by_count":26},{"id":"2211.10257","title":"Model-based Causal Bayesian Optimization","created":"2022-11-18","cited_by_count":26},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22},{"id":"2007.06482","title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation","created":"2020-07-13","cited_by_count":18},{"id":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18},{"id":"1711.07230","title":"Optimism-Based Adaptive Regulation of Linear-Quadratic Systems","created":"2017-11-20","cited_by_count":14},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","cited_by_count":8},{"id":"2403.16644","title":"Bridging the Sim-to-Real Gap with Bayesian Inference","created":"2024-03-25","cited_by_count":8},{"id":"2312.14788","title":"Harnessing Uncertainty for a Separation Principle in Direct Data-Driven Predictive Control","created":"2023-12-22","cited_by_count":4},{"id":"2409.16717","title":"The Bayesian Separation Principle for Data-driven Control","created":"2024-09-25","cited_by_count":2}],"next_cursor":null}