{"list":"other","total":57,"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","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":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"id":"1906.08383","title":"Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies","created":"2019-06-19","cited_by_count":124},{"id":"2005.01350","title":"A Finite Time Analysis of Two Time-Scale Actor Critic Methods","created":"2020-05-04","cited_by_count":122},{"id":"2011.02669","title":"Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping","created":"2020-11-05","cited_by_count":114},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2010.11364","title":"Sample Efficient Reinforcement Learning with REINFORCE","created":"2020-10-22","cited_by_count":86},{"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":"2006.04045","title":"A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton","created":"2020-06-07","cited_by_count":79},{"id":"1702.03999","title":"A First Order Method for Solving Convex Bi-Level Optimization Problems","created":"2017-02-13","cited_by_count":67},{"id":"2006.08910","title":"Preference-based Reinforcement Learning with Finite-Time Guarantees","created":"2020-06-16","cited_by_count":65},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63},{"id":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53},{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"1901.09330","title":"Reward Shaping via Meta-Learning","created":"2019-01-27","cited_by_count":32},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31},{"id":"2102.07976","title":"A General Descent Aggregation Framework for Gradient-based Bi-level Optimization","created":"2021-02-16","cited_by_count":28},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28},{"id":"2012.15511","title":"Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup","created":"2020-12-31","cited_by_count":25},{"id":"2206.00457","title":"Automatic differentiation of nonsmooth iterative algorithms","created":"2022-05-31","cited_by_count":25},{"id":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","cited_by_count":22},{"id":"2112.10859","title":"Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning","created":"2021-12-20","cited_by_count":19},{"id":"1811.01213","title":"Learning to Defend by Learning to Attack","created":"2018-11-03","cited_by_count":17},{"id":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17},{"id":"2210.02515","title":"Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems","created":"2022-10-03","cited_by_count":13},{"id":"2110.00604","title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems","created":"2021-10-01","cited_by_count":11},{"id":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","cited_by_count":10},{"id":"2303.03095","title":"Can We Find Nash Equilibria at a Linear Rate in Markov Games?","created":"2023-03-03","cited_by_count":9},{"id":"1603.00244","title":"Caching Incentive Design in Wireless D2D Networks: A Stackelberg Game Approach","created":"2016-03-01","cited_by_count":3}],"next_cursor":null}