{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1809.03672","title":"Deep Interest Evolution Network for Click-Through Rate Prediction","created":"2018-09-11","cited_by_count":338},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"1803.02349","title":"Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba","created":"2018-03-06","cited_by_count":105},{"id":"1706.04972","title":"Device Placement Optimization with Reinforcement Learning","created":"2017-06-13","cited_by_count":86},{"id":"1906.03109","title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation","created":"2019-06-06","cited_by_count":83},{"id":"1909.04063","title":"Exploratory Combinatorial Optimization with Reinforcement Learning","created":"2019-09-09","cited_by_count":82},{"id":"1909.02107","title":"Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems","created":"2019-09-04","cited_by_count":68},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66},{"id":"2003.05622","title":"Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems","created":"2020-03-12","cited_by_count":60},{"id":"2108.13342","title":"DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion","created":"2021-08-30","cited_by_count":57},{"id":"2002.11252","title":"AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations","created":"2020-02-26","cited_by_count":47},{"id":"2011.05497","title":"Understanding Training Efficiency of Deep Learning Recommendation Models at Scale","created":"2020-11-11","cited_by_count":43},{"id":"2101.07577","title":"Learnable Embedding Sizes for Recommender Systems","created":"2021-01-19","cited_by_count":42},{"id":"2009.09822","title":"TODS: An Automated Time Series Outlier Detection System","created":"2020-09-18","cited_by_count":41},{"id":"2101.05615","title":"FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference","created":"2021-01-13","cited_by_count":41},{"id":"1907.04471","title":"Neural Input Search for Large Scale Recommendation Models","created":"2019-07-10","cited_by_count":39},{"id":"2003.09518","title":"Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems","created":"2020-03-20","cited_by_count":38},{"id":"2010.10784","title":"Learning to Embed Categorical Features without Embedding Tables for Recommendation","created":"2020-10-21","cited_by_count":38},{"id":"2009.07415","title":"Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning","created":"2020-09-16","cited_by_count":34},{"id":"2007.14523","title":"Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems","created":"2020-07-28","cited_by_count":33},{"id":"2011.02084","title":"Understanding Capacity-Driven Scale-Out Neural Recommendation Inference","created":"2020-11-04","cited_by_count":29},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28},{"id":"2201.10095","title":"RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation","created":"2022-01-25","cited_by_count":28},{"id":"1906.08879","title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","created":"2019-06-20","cited_by_count":26},{"id":"1702.07969","title":"Related Pins at Pinterest: The Evolution of a Real-World Recommender System","created":"2017-02-26","cited_by_count":24},{"id":"2002.08530","title":"Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems","created":"2020-02-20","cited_by_count":24},{"id":"2006.16423","title":"Efficient Algorithms for Device Placement of DNN Graph Operators","created":"2020-06-29","cited_by_count":24},{"id":"2111.02508","title":"AlphaD3M: Machine Learning Pipeline Synthesis","created":"2021-11-03","cited_by_count":24},{"id":"1802.04924","title":"Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks","created":"2018-02-14","cited_by_count":23},{"id":"1905.02494","title":"Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs","created":"2019-05-07","cited_by_count":17},{"id":"2208.06399","title":"AutoShard: Automated Embedding Table Sharding for Recommender Systems","created":"2022-08-12","cited_by_count":17},{"id":"2205.13748","title":"Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture","created":"2022-05-27","cited_by_count":14},{"id":"1910.01578","title":"GDP: Generalized Device Placement for Dataflow Graphs","created":"2019-09-28","cited_by_count":10},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9},{"id":"2208.12433","title":"Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning","created":"2022-08-26","cited_by_count":9},{"id":"2003.08445","title":"Placement Optimization with Deep Reinforcement Learning","created":"2020-03-18","cited_by_count":7},{"id":"2108.04212","title":"AutoVideo: An Automated Video Action Recognition System","created":"2021-08-09","cited_by_count":6}],"next_cursor":null}