{"list":"other","total":89,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"1804.07795","title":"Stochastic subgradient method converges on tame functions","created":"2018-04-20","cited_by_count":124},{"id":"2007.02151","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","created":"2020-07-04","cited_by_count":111},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108},{"id":"2010.11364","title":"Sample Efficient Reinforcement Learning with REINFORCE","created":"2020-10-22","cited_by_count":86},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70},{"id":"1605.00125","title":"Efficiency of minimizing compositions of convex functions and smooth maps","created":"2016-04-30","cited_by_count":59},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56},{"id":"1908.02734","title":"Stochastic First-order Methods for Convex and Nonconvex Functional Constrained Optimization","created":"2019-08-07","cited_by_count":38},{"id":"2202.03060","title":"The Importance of Non-Markovianity in Maximum State Entropy Exploration","created":"2022-02-07","cited_by_count":35},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34},{"id":"1803.02461","title":"Subgradient methods for sharp weakly convex functions","created":"2018-03-06","cited_by_count":33},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33},{"id":"1802.02988","title":"Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions","created":"2018-02-08","cited_by_count":32},{"id":"2206.11889","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","created":"2022-06-23","cited_by_count":31},{"id":"1707.03505","title":"Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems","created":"2017-07-12","cited_by_count":30},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27},{"id":"1908.01871","title":"Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints","created":"2019-08-05","cited_by_count":25},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23},{"id":"2307.13372","title":"Submodular Reinforcement Learning","created":"2023-07-25","cited_by_count":23},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22},{"id":"1711.05812","title":"Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming","created":"2017-11-15","cited_by_count":21},{"id":"2007.01284","title":"Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization","created":"2020-07-02","cited_by_count":21},{"id":"1907.04662","title":"An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies","created":"2019-07-10","cited_by_count":20},{"id":"2206.05850","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm","created":"2022-06-12","cited_by_count":20},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19},{"id":"2212.09513","title":"Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization","created":"2022-12-19","cited_by_count":19},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19},{"id":"2006.14901","title":"Understanding Notions of Stationarity in Non-Smooth Optimization","created":"2020-06-26","cited_by_count":18},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18},{"id":"1908.00131","title":"Complexity of Proximal augmented Lagrangian for nonconvex optimization with nonlinear equality constraints","created":"2019-07-31","cited_by_count":17},{"id":"2212.00927","title":"First-Order Methods for Nonsmooth Nonconvex Functional Constrained Optimization with or without Slater Points","created":"2022-12-02","cited_by_count":17},{"id":"1711.03247","title":"The nonsmooth landscape of phase retrieval","created":"2017-11-09","cited_by_count":16},{"id":"1912.05128","title":"Marginalized State Distribution Entropy Regularization in Policy Optimization","created":"2019-12-11","cited_by_count":16},{"id":"1802.03504","title":"Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs","created":"2018-02-10","cited_by_count":15},{"id":"1812.10229","title":"A Proximal Alternating Direction Method of Multiplier for Linearly Constrained Nonconvex Minimization","created":"2018-12-26","cited_by_count":14},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14},{"id":"2401.00108","title":"Stochastic Optimization under Hidden Convexity","created":"2023-12-30","cited_by_count":12},{"id":"1610.04514","title":"The proximal augmented Lagrangian method for nonsmooth composite optimization","created":"2016-10-14","cited_by_count":11},{"id":"2301.13314","title":"Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization","created":"2023-01-30","cited_by_count":11},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10},{"id":"2402.17885","title":"Independent Learning in Constrained Markov Potential Games","created":"2024-02-27","cited_by_count":10},{"id":"2501.19214","title":"A single-loop SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization","created":"2025-01-31","cited_by_count":9},{"id":"2205.08011","title":"Level Constrained First Order Methods for Function Constrained Optimization","created":"2022-05-16","cited_by_count":8},{"id":"1506.05320","title":"Complexity of first order inexact Lagrangian and penalty methods for conic convex programming","created":"2015-06-17","cited_by_count":7},{"id":"1603.05738","title":"On the non-ergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming","created":"2016-03-18","cited_by_count":7},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7},{"id":"2311.13589","title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions","created":"2023-11-22","cited_by_count":7},{"id":"2311.18346","title":"Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent","created":"2023-11-30","cited_by_count":6},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6},{"id":"2504.15243","title":"Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints","created":"2025-04-21","cited_by_count":6},{"id":"2505.06053","title":"Safe-EF: Error Feedback for Nonsmooth Constrained Optimization","created":"2025-05-09","cited_by_count":6},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6},{"id":"1505.03175","title":"Adaptive inexact fast augmented Lagrangian methods for constrained convex optimization","created":"2015-05-12","cited_by_count":5},{"id":"2205.10715","title":"Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction","created":"2022-05-22","cited_by_count":5},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5},{"id":"2505.20628","title":"Position: Adopt Constraints Over Fixed Penalties in Deep Learning","created":"2025-05-27","cited_by_count":5},{"id":"2410.03955","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","created":"2024-10-04","cited_by_count":4},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4},{"id":"2505.02495","title":"An Exact Penalty Approach for Equality Constrained Optimization over a Convex Set","created":"2025-05-05","cited_by_count":4},{"id":"2409.15128","title":"The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes","created":"2024-09-23","cited_by_count":3},{"id":"2302.07938","title":"Scalable Multi-Agent Reinforcement Learning with General Utilities","created":"2023-02-15","cited_by_count":2},{"id":"2511.10626","title":"Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity","created":"2025-11-13","cited_by_count":2},{"id":"2208.14019","title":"Robins-Monro Augmented Lagrangian Method for Stochastic Convex Optimization","created":"2022-08-30","cited_by_count":1},{"id":"2303.15349","title":"Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills","created":"2023-03-27","cited_by_count":1},{"id":"2308.06470","title":"On the Optimal Lower and Upper Complexity Bounds for a Class of Composite Optimization Problems","created":"2023-08-12","cited_by_count":1},{"id":"2309.14096","title":"Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":1}],"next_cursor":null}