{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"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":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1706.02633","title":"Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs","created":"2017-06-08","cited_by_count":333},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"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":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"1711.08946","title":"Action Branching Architectures for Deep Reinforcement Learning","created":"2017-11-24","cited_by_count":92},{"id":"2002.05786","title":"Deep Learning for Financial Applications : A Survey","created":"2020-02-09","cited_by_count":91},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"1911.10107","title":"Deep Reinforcement Learning for Trading","created":"2019-11-22","cited_by_count":73},{"id":"1806.08946","title":"Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis","created":"2018-06-23","cited_by_count":61},{"id":"2003.10014","title":"Reinforcement Learning in Economics and Finance","created":"2020-03-22","cited_by_count":58},{"id":"2002.05780","title":"Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States","created":"2020-02-09","cited_by_count":55},{"id":"1912.03193","title":"Risk-Averse Trust Region Optimization for Reward-Volatility Reduction","created":"2019-12-06","cited_by_count":54},{"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":"1812.06600","title":"Double Deep Q-Learning for Optimal Execution","created":"2018-12-17","cited_by_count":43},{"id":"1908.02646","title":"AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks","created":"2019-07-24","cited_by_count":40},{"id":"1910.04450","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","created":"2019-10-10","cited_by_count":40},{"id":"1911.05892","title":"Reinforcement Learning for Market Making in a Multi-agent Dealer Market","created":"2019-11-14","cited_by_count":39},{"id":"2010.13303","title":"Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning","created":"2020-10-26","cited_by_count":35},{"id":"2004.06627","title":"An Application of Deep Reinforcement Learning to Algorithmic Trading","created":"2020-04-07","cited_by_count":30},{"id":"2103.10860","title":"Universal Trading for Order Execution with Oracle Policy Distillation","created":"2021-01-28","cited_by_count":30},{"id":"2103.16409","title":"Deep Hedging of Derivatives Using Reinforcement Learning","created":"2021-03-29","cited_by_count":30},{"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":"1807.02787","title":"Financial Trading as a Game: A Deep Reinforcement Learning Approach","created":"2018-07-08","cited_by_count":22},{"id":"1901.08740","title":"Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization","created":"2019-01-25","cited_by_count":22},{"id":"2003.03051","title":"Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning","created":"2020-03-06","cited_by_count":21},{"id":"2101.07107","title":"Deep Reinforcement Learning for Active High Frequency Trading","created":"2021-01-18","cited_by_count":21},{"id":"2012.12620","title":"Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution","created":"2020-12-23","cited_by_count":20},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20},{"id":"1906.11046","title":"Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis","created":"2019-06-24","cited_by_count":15},{"id":"2007.05402","title":"MAPS: Multi-agent Reinforcement Learning-based Portfolio Management System","created":"2020-07-10","cited_by_count":15},{"id":"1904.10554","title":"Deep Q-Learning for Nash Equilibria: Nash-DQN","created":"2019-04-23","cited_by_count":14},{"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":"2003.01820","title":"Robust Market Making via Adversarial Reinforcement Learning","created":"2020-03-03","cited_by_count":14},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","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":"2010.12245","title":"Option Hedging with Risk Averse Reinforcement Learning","created":"2020-10-23","cited_by_count":13},{"id":"2105.08664","title":"Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket","created":"2021-05-06","cited_by_count":13},{"id":"2102.03502","title":"MSPM: A Modularized and Scalable Multi-Agent Reinforcement Learning-based System for Financial Portfolio Management","created":"2021-02-06","cited_by_count":10},{"id":"2002.10990","title":"G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning","created":"2020-02-25","cited_by_count":9},{"id":"1612.00385","title":"Temporal Attention-Gated Model for Robust Sequence Classification","created":"2016-12-01","cited_by_count":8},{"id":"1911.02067","title":"Robo-advising: Learning Investors' Risk Preferences via Portfolio Choices","created":"2019-11-05","cited_by_count":7},{"id":"2010.14194","title":"Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning","created":"2020-10-27","cited_by_count":7},{"id":"2105.09264","title":"Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning","created":"2021-05-19","cited_by_count":7},{"id":"1807.06824","title":"News-based trading strategies","created":"2018-07-18","cited_by_count":5},{"id":"1907.11718","title":"Large scale continuous-time mean-variance portfolio allocation via reinforcement learning","created":"2019-07-26","cited_by_count":5},{"id":"2001.00918","title":"Fairness in Multi-agent Reinforcement Learning for Stock Trading","created":"2019-12-14","cited_by_count":5},{"id":"2010.09108","title":"Bridging the gap between Markowitz planning and deep reinforcement learning","created":"2020-09-30","cited_by_count":5},{"id":"2011.04391","title":"Reinforced Deep Markov Models With Applications in Automatic Trading","created":"2020-11-09","cited_by_count":5},{"id":"2002.11523","title":"Using Reinforcement Learning in the Algorithmic Trading Problem","created":"2020-02-26","cited_by_count":4},{"id":"2009.07200","title":"Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning","created":"2020-09-07","cited_by_count":4},{"id":"2201.04699","title":"The Recurrent Reinforcement Learning Crypto Agent","created":"2022-01-12","cited_by_count":4},{"id":"2110.04745","title":"Reinforcement Learning for Systematic FX Trading","created":"2021-10-10","cited_by_count":3},{"id":"2010.01687","title":"Learning Risk Preferences from Investment Portfolios Using Inverse Optimization","created":"2020-10-04","cited_by_count":2},{"id":"2010.08497","title":"AAMDRL: Augmented Asset Management with Deep Reinforcement Learning","created":"2020-09-30","cited_by_count":1},{"id":"2104.10483","title":"Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting","created":"2021-04-19","cited_by_count":1}],"next_cursor":null}