{"list":"other","total":55,"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1908.09970","title":"Private Stochastic Convex Optimization with Optimal Rates","created":"2019-08-27","cited_by_count":186},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161},{"id":"1909.01150","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","created":"2019-08-29","cited_by_count":159},{"id":"2005.04763","title":"Private Stochastic Convex Optimization: Optimal Rates in Linear Time","created":"2020-05-10","cited_by_count":153},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"1806.05618","title":"Stochastic Variance-Reduced Policy Gradient","created":"2018-06-14","cited_by_count":106},{"id":"2007.08459","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","created":"2020-07-16","cited_by_count":92},{"id":"2103.01516","title":"Private Stochastic Convex Optimization: Optimal Rates in $\\ell_1$ Geometry","created":"2021-03-02","cited_by_count":83},{"id":"1810.00068","title":"Differentially Private Contextual Linear Bandits","created":"2018-09-28","cited_by_count":82},{"id":"2002.08243","title":"Optimistic Policy Optimization with Bandit Feedback","created":"2020-02-19","cited_by_count":79},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68},{"id":"1803.02596","title":"Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain","created":"2018-03-07","cited_by_count":61},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"2009.09052","title":"Private Reinforcement Learning with PAC and Regret Guarantees","created":"2020-09-18","cited_by_count":51},{"id":"2103.01278","title":"Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time","created":"2021-03-01","cited_by_count":51},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46},{"id":"1906.10306","title":"Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy","created":"2019-06-25","cited_by_count":43},{"id":"1905.09383","title":"An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rule","created":"2019-05-22","cited_by_count":37},{"id":"2007.03121","title":"Multi-Armed Bandits with Local Differential Privacy","created":"2020-07-06","cited_by_count":37},{"id":"2206.00846","title":"Faster Rates of Convergence to Stationary Points in Differentially Private Optimization","created":"2022-06-02","cited_by_count":32},{"id":"2106.09779","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","created":"2021-06-17","cited_by_count":30},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30},{"id":"2202.05567","title":"Shuffle Private Linear Contextual Bandits","created":"2022-02-11","cited_by_count":27},{"id":"2006.13501","title":"Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds","created":"2020-06-24","cited_by_count":26},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26},{"id":"1311.2828","title":"Private Matchings and Allocations","created":"2013-11-12","cited_by_count":23},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22},{"id":"2103.15352","title":"Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps","created":"2021-03-29","cited_by_count":21},{"id":"1603.02010","title":"Differentially Private Policy Evaluation","created":"2016-03-07","cited_by_count":19},{"id":"2310.16960","title":"Privately Aligning Language Models with Reinforcement Learning","created":"2023-10-25","cited_by_count":17},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16},{"id":"2206.05772","title":"Distributed Differential Privacy in Multi-Armed Bandits","created":"2022-06-12","cited_by_count":14},{"id":"2302.13945","title":"On Differentially Private Federated Linear Contextual Bandits","created":"2023-02-27","cited_by_count":14},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13},{"id":"2302.09699","title":"Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks","created":"2023-02-20","cited_by_count":12},{"id":"2402.13531","title":"Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation","created":"2024-02-21","cited_by_count":12},{"id":"2112.01585","title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","created":"2021-12-02","cited_by_count":11},{"id":"2009.06108","title":"Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multi-Armed Bandit Approach","created":"2020-09-13","cited_by_count":10},{"id":"2407.09690","title":"Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses","created":"2024-07-12","cited_by_count":8},{"id":"2404.15409","title":"Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares","created":"2024-04-23","cited_by_count":7},{"id":"2302.02526","title":"On Private and Robust Bandits","created":"2023-02-06","cited_by_count":6},{"id":"2501.19080","title":"Differentially Private Policy Gradient","created":"2025-01-31","cited_by_count":3},{"id":"2410.07502","title":"Adaptive Batch Size for Privately Finding Second-Order Stationary Points","created":"2024-10-10","cited_by_count":2},{"id":"2503.24321","title":"Sample-Optimal Private Regression in Polynomial Time","created":"2025-03-31","cited_by_count":2}],"next_cursor":null}