{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"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":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"1301.2609","title":"Learning to Optimize Via Posterior Sampling","created":"2013-01-11","cited_by_count":256},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"2104.12225","title":"DC3: A learning method for optimization with hard constraints","created":"2021-04-25","cited_by_count":184},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2206.05229","title":"Measuring the Carbon Intensity of AI in Cloud Instances","created":"2022-06-10","cited_by_count":111},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"1804.07193","title":"Lipschitz Continuity in Model-based Reinforcement Learning","created":"2018-04-19","cited_by_count":91},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66},{"id":"1602.04282","title":"Conservative Bandits","created":"2016-02-13","cited_by_count":59},{"id":"2110.00675","title":"Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview","created":"2021-10-01","cited_by_count":45},{"id":"2106.11750","title":"Carbon-Aware Computing for Datacenters","created":"2021-06-11","cited_by_count":41},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35},{"id":"2105.08881","title":"Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization","created":"2021-05-19","cited_by_count":31},{"id":"2206.11889","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","created":"2022-06-23","cited_by_count":31},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29},{"id":"2106.10497","title":"Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems","created":"2021-06-19","cited_by_count":25},{"id":"2102.01309","title":"On the Regret Analysis of Online LQR Control with Predictions","created":"2021-02-02","cited_by_count":22},{"id":"2002.03218","title":"Conservative Exploration in Reinforcement Learning","created":"2020-02-08","cited_by_count":20},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19},{"id":"2210.12312","title":"Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity","created":"2022-10-22","cited_by_count":16},{"id":"2010.00412","title":"Competitive Algorithms for the Online Multiple Knapsack Problem with Application to Electric Vehicle Charging","created":"2020-10-01","cited_by_count":15},{"id":"2109.14854","title":"Stability Constrained Reinforcement Learning for Real-Time Voltage Control","created":"2021-09-30","cited_by_count":15},{"id":"2212.12735","title":"An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context","created":"2022-12-24","cited_by_count":15},{"id":"2106.09659","title":"Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions","created":"2021-06-17","cited_by_count":14},{"id":"2111.00411","title":"Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees","created":"2021-10-31","cited_by_count":11},{"id":"2112.05198","title":"Reinforcement Learning with Almost Sure Constraints","created":"2021-12-09","cited_by_count":11},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9},{"id":"2207.13131","title":"Semi-analytical Industrial Cooling System Model for Reinforcement Learning","created":"2022-07-26","cited_by_count":9},{"id":"2301.08445","title":"Online switching control with stability and regret guarantees","created":"2023-01-20","cited_by_count":9},{"id":"2204.08572","title":"Expert-Calibrated Learning for Online Optimization with Switching Costs","created":"2022-04-18","cited_by_count":6},{"id":"2012.07341","title":"A One-Size-Fits-All Solution to Conservative Bandit Problems","created":"2020-12-14","cited_by_count":5},{"id":"2210.00596","title":"Policy Gradients for Probabilistic Constrained Reinforcement Learning","created":"2022-10-02","cited_by_count":5},{"id":"1806.00892","title":"Conservative Exploration using Interleaving","created":"2018-06-03","cited_by_count":4},{"id":"2305.00677","title":"Robustified Learning for Online Optimization with Memory Costs","created":"2023-05-01","cited_by_count":4},{"id":"1801.02015","title":"Reverse and Forward Engineering of Local Voltage Control in Distribution Networks","created":"2018-01-06","cited_by_count":3},{"id":"2002.08908","title":"Asymptotically Optimal Load Balancing in Large-scale Heterogeneous Systems with Multiple Dispatchers","created":"2020-02-20","cited_by_count":3},{"id":"2209.08112","title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","created":"2022-09-16","cited_by_count":2},{"id":"1806.02939","title":"Flexible Load Balancing with Multi-dimensional State-space Collapse: Throughput and Heavy-traffic Delay Optimality","created":"2018-06-08","cited_by_count":1}],"next_cursor":null}