{"list":"other","total":52,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"id":"1908.00261","title":"On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift","created":"2019-08-01","cited_by_count":177},{"id":"1507.04888","title":"Maximum Entropy Deep Inverse Reinforcement Learning","created":"2015-07-17","cited_by_count":176},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155},{"id":"1906.08383","title":"Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies","created":"2019-06-19","cited_by_count":124},{"id":"1802.03042","title":"Deep Hedging","created":"2018-02-08","cited_by_count":108},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"id":"1807.11398","title":"Preference-based Online Learning with Dueling Bandits: A Survey","created":"2018-07-30","cited_by_count":102},{"id":"1502.06362","title":"Contextual Dueling Bandits","created":"2015-02-23","cited_by_count":101},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"id":"2102.04671","title":"A Single-Timescale Method for Stochastic Bilevel Optimization","created":"2021-02-09","cited_by_count":69},{"id":"2006.08910","title":"Preference-based Reinforcement Learning with Finite-Time Guarantees","created":"2020-06-16","cited_by_count":65},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53},{"id":"1605.08478","title":"Model-Free Imitation Learning with Policy Optimization","created":"2016-05-26","cited_by_count":52},{"id":"2007.11120","title":"On Linear Convergence of Policy Gradient Methods for Finite MDPs","created":"2020-07-21","cited_by_count":52},{"id":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46},{"id":"2102.11494","title":"Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games","created":"2021-02-23","cited_by_count":40},{"id":"1906.01217","title":"Convergence of Learning Dynamics in Stackelberg Games","created":"2019-06-04","cited_by_count":28},{"id":"2107.12301","title":"Enhanced Bilevel Optimization via Bregman Distance","created":"2021-07-26","cited_by_count":28},{"id":"2302.03407","title":"Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity","created":"2023-02-07","cited_by_count":26},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20},{"id":"1504.01033","title":"Watch and Learn: Optimizing from Revealed Preferences Feedback","created":"2015-04-04","cited_by_count":17},{"id":"2303.03944","title":"On Momentum-Based Gradient Methods for Bilevel Optimization with Nonconvex Lower-Level","created":"2023-03-07","cited_by_count":14},{"id":"1301.3873","title":"Credal Networks under Maximum Entropy","created":"2013-01-16","cited_by_count":13},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11},{"id":"2103.16977","title":"Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":10},{"id":"1407.7937","title":"Learning Economic Parameters from Revealed Preferences","created":"2014-07-30","cited_by_count":8},{"id":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8},{"id":"1806.00206","title":"Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing","created":"2018-06-01","cited_by_count":7},{"id":"2206.01162","title":"Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning","created":"2022-06-02","cited_by_count":7},{"id":"1902.06766","title":"Parenting: Safe Reinforcement Learning from Human Input","created":"2019-02-18","cited_by_count":6},{"id":"2202.12797","title":"Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach","created":"2022-02-25","cited_by_count":5},{"id":"2205.02450","title":"Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning","created":"2022-05-05","cited_by_count":4},{"id":"1906.07611","title":"Simple Algorithms for Dueling Bandits","created":"2019-06-18","cited_by_count":3},{"id":"2206.05652","title":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies","created":"2022-06-12","cited_by_count":2},{"id":"2211.13847","title":"Zero-Sum Stochastic Stackelberg Games","created":"2022-11-25","cited_by_count":2},{"id":"2301.06421","title":"AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents","created":"2023-01-16","cited_by_count":1}],"next_cursor":null}