{"list":"other","total":51,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1708.05123","title":"Deep & Cross Network for Ad Click Predictions","created":"2017-08-17","cited_by_count":393},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1906.07682","title":"Parameterized quantum circuits as machine learning models","created":"2019-06-18","cited_by_count":332},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122},{"id":"1804.04168","title":"Differentiable Learning of Quantum Circuit Born Machine","created":"2018-04-11","cited_by_count":93},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"2111.15367","title":"A Review on Graph Neural Network Methods in Financial Applications","created":"2021-11-27","cited_by_count":78},{"id":"1806.06871","title":"Continuous-variable quantum neural networks","created":"2018-06-18","cited_by_count":74},{"id":"1603.08675","title":"Quantum Recommendation Systems","created":"2016-03-29","cited_by_count":70},{"id":"1807.04271","title":"A quantum-inspired classical algorithm for recommendation systems","created":"2018-07-10","cited_by_count":70},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"1803.10760","title":"Unsupervised Predictive Memory in a Goal-Directed Agent","created":"2018-03-28","cited_by_count":55},{"id":"1602.09046","title":"On Complex Valued Convolutional Neural Networks","created":"2016-02-29","cited_by_count":26}],"next_cursor":null}