{"list":"other","total":111,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1806.02450","title":"A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation","created":"2018-06-06","cited_by_count":229},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"1909.01150","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","created":"2019-08-29","cited_by_count":159},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"1311.2097","title":"Risk-sensitive Reinforcement Learning","created":"2013-11-08","cited_by_count":130},{"id":"1706.10059","title":"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem","created":"2017-06-30","cited_by_count":128},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"1911.07676","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","created":"2019-11-18","cited_by_count":127},{"id":"1906.08383","title":"Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies","created":"2019-06-19","cited_by_count":124},{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124},{"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":"2003.12699","title":"Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability","created":"2020-03-28","cited_by_count":115},{"id":"2005.12900","title":"Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model","created":"2020-05-26","cited_by_count":109},{"id":"1802.03042","title":"Deep Hedging","created":"2018-02-08","cited_by_count":108},{"id":"1907.06673","title":"Quant GANs: Deep Generation of Financial Time Series","created":"2019-07-15","cited_by_count":108},{"id":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","cited_by_count":106},{"id":"1806.05618","title":"Stochastic Variance-Reduced Policy Gradient","created":"2018-06-14","cited_by_count":106},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101},{"id":"1904.01763","title":"Batched Multi-armed Bandits Problem","created":"2019-04-03","cited_by_count":98},{"id":"2102.05406","title":"Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach","created":"2021-02-10","cited_by_count":98},{"id":"2010.11364","title":"Sample Efficient Reinforcement Learning with REINFORCE","created":"2020-10-22","cited_by_count":86},{"id":"1902.02234","title":"Finite-Sample Analysis for SARSA with Linear Function Approximation","created":"2019-02-06","cited_by_count":85},{"id":"2108.06655","title":"Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach","created":"2021-08-15","cited_by_count":84},{"id":"1910.07072","title":"Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes","created":"2019-10-15","cited_by_count":82},{"id":"1502.03919","title":"Policy Gradient for Coherent Risk Measures","created":"2015-02-13","cited_by_count":76},{"id":"2006.14389","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","created":"2020-06-24","cited_by_count":76},{"id":"1911.10107","title":"Deep Reinforcement Learning for Trading","created":"2019-11-22","cited_by_count":73},{"id":"1709.04570","title":"Learning Unknown Markov Decision Processes: A Thompson Sampling Approach","created":"2017-09-14","cited_by_count":65},{"id":"1909.08610","title":"Sample Efficient Policy Gradient Methods with Recursive Variance Reduction","created":"2019-09-18","cited_by_count":60},{"id":"1602.04282","title":"Conservative Bandits","created":"2016-02-13","cited_by_count":59},{"id":"1905.12615","title":"An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient","created":"2019-05-29","cited_by_count":59},{"id":"2003.10014","title":"Reinforcement Learning in Economics and Finance","created":"2020-03-22","cited_by_count":58},{"id":"2006.13827","title":"Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret","created":"2020-06-22","cited_by_count":58},{"id":"2111.09395","title":"FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance","created":"2021-11-07","cited_by_count":58},{"id":"1901.09311","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","created":"2019-01-27","cited_by_count":55},{"id":"1910.08412","title":"On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation","created":"2019-10-18","cited_by_count":54},{"id":"2011.10300","title":"Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon","created":"2020-11-20","cited_by_count":50},{"id":"1811.07522","title":"Practical Deep Reinforcement Learning Approach for Stock Trading","created":"2018-11-19","cited_by_count":49},{"id":"1804.04216","title":"Market Making via Reinforcement Learning","created":"2018-04-11","cited_by_count":47},{"id":"1912.04511","title":"A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation","created":"2019-12-10","cited_by_count":47},{"id":"1903.01461","title":"Hedging the Drift: Learning to Optimize under Non-Stationarity","created":"2019-03-04","cited_by_count":46},{"id":"2001.09377","title":"Constrained Upper Confidence Reinforcement Learning","created":"2020-01-26","cited_by_count":46},{"id":"1812.06600","title":"Double Deep Q-Learning for Optimal Execution","created":"2018-12-17","cited_by_count":43},{"id":"2005.03557","title":"Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms","created":"2020-05-07","cited_by_count":43},{"id":"1911.05892","title":"Reinforcement Learning for Market Making in a Multi-agent Dealer Market","created":"2019-11-14","cited_by_count":39},{"id":"2006.15316","title":"Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon","created":"2020-06-27","cited_by_count":35},{"id":"2008.00483","title":"Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy","created":"2020-08-02","cited_by_count":34},{"id":"2109.10269","title":"Exploratory HJB equations and their convergence","created":"2021-09-21","cited_by_count":32},{"id":"1904.05526","title":"A Selective Overview of Deep Learning","created":"2019-04-10","cited_by_count":31},{"id":"1805.10066","title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","created":"2018-05-25","cited_by_count":30},{"id":"2103.16409","title":"Deep Hedging of Derivatives Using Reinforcement Learning","created":"2021-03-29","cited_by_count":30},{"id":"2006.01782","title":"Temporally-Extended {\\epsilon}-Greedy Exploration","created":"2020-06-02","cited_by_count":29},{"id":"2010.12870","title":"Efficient Learning in Non-Stationary Linear Markov Decision Processes","created":"2020-10-24","cited_by_count":26},{"id":"2104.09311","title":"Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls","created":"2021-04-19","cited_by_count":24},{"id":"1712.04609","title":"QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds","created":"2017-12-13","cited_by_count":23},{"id":"2004.01509","title":"Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics","created":"2020-03-21","cited_by_count":23},{"id":"1901.08740","title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","created":"2019-01-25","cited_by_count":22},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21},{"id":"2002.03218","title":"Conservative Exploration in Reinforcement Learning","created":"2020-02-08","cited_by_count":20},{"id":"2011.07456","title":"State-Dependent Temperature Control for Langevin Diffusions","created":"2020-11-15","cited_by_count":20},{"id":"1812.01552","title":"Exploration versus exploitation in reinforcement learning: a stochastic control approach","created":"2018-12-04","cited_by_count":18},{"id":"2108.10403","title":"Robust Risk-Aware Reinforcement Learning","created":"2021-08-23","cited_by_count":18},{"id":"1906.06273","title":"Epistemic Risk-Sensitive Reinforcement Learning","created":"2019-06-14","cited_by_count":17},{"id":"2010.03161","title":"Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control","created":"2020-10-07","cited_by_count":17},{"id":"1709.07796","title":"On overfitting and asymptotic bias in batch reinforcement learning with partial observability","created":"2017-09-22","cited_by_count":16},{"id":"1906.11046","title":"Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis","created":"2019-06-24","cited_by_count":15},{"id":"2002.06286","title":"Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling","created":"2020-02-15","cited_by_count":15},{"id":"1907.03665","title":"An intelligent financial portfolio trading strategy using deep Q-learning","created":"2019-07-08","cited_by_count":14},{"id":"1910.03743","title":"Model-based Reinforcement Learning for Predictions and Control for Limit Order Books","created":"2019-10-09","cited_by_count":14},{"id":"1812.10252","title":"Optimizing Market Making using Multi-Agent Reinforcement Learning","created":"2018-12-26","cited_by_count":13},{"id":"2009.14257","title":"Finite-Time Analysis for Double Q-learning","created":"2020-09-29","cited_by_count":12}],"next_cursor":"100"}