{"list":"other","total":107,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1509.09292","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","created":"2015-09-30","cited_by_count":754},{"id":"1803.01422","title":"DAGs with NO TEARS: Continuous Optimization for Structure Learning","created":"2018-03-04","cited_by_count":752},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","cited_by_count":652},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1802.08773","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","created":"2018-02-24","cited_by_count":413},{"id":"1805.11973","title":"MolGAN: An implicit generative model for small molecular graphs","created":"2018-05-30","cited_by_count":393},{"id":"1806.02473","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","created":"2018-06-07","cited_by_count":364},{"id":"2010.16011","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","created":"2020-10-30","cited_by_count":348},{"id":"1806.02371","title":"Adversarial Attack on Graph Structured Data","created":"2018-06-06","cited_by_count":301},{"id":"1703.01925","title":"Grammar Variational Autoencoder","created":"2017-03-06","cited_by_count":285},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1910.00760","title":"Efficient Graph Generation with Graph Recurrent Attention Networks","created":"2019-10-02","cited_by_count":234},{"id":"1803.03324","title":"Learning Deep Generative Models of Graphs","created":"2018-03-08","cited_by_count":229},{"id":"1704.03165","title":"struc2vec: Learning Node Representations from Structural Identity","created":"2017-04-11","cited_by_count":215},{"id":"1810.08678","title":"Optimization of Molecules via Deep Reinforcement Learning","created":"2018-10-19","cited_by_count":200},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1512.07679","title":"Deep Reinforcement Learning in Large Discrete Action Spaces","created":"2015-12-24","cited_by_count":161},{"id":"1711.05851","title":"Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning","created":"2017-11-15","cited_by_count":161},{"id":"1905.13211","title":"What Can Neural Networks Reason About?","created":"2019-05-30","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":"2206.12411","title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","created":"2022-06-22","cited_by_count":155},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"id":"2202.05146","title":"EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction","created":"2022-02-07","cited_by_count":144},{"id":"1603.05629","title":"Discriminative Embeddings of Latent Variable Models for Structured Data","created":"2016-03-17","cited_by_count":131},{"id":"2205.13209","title":"Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization","created":"2022-05-26","cited_by_count":119},{"id":"1705.10843","title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models","created":"2017-05-30","cited_by_count":117},{"id":"1911.09539","title":"Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem","created":"2019-11-21","cited_by_count":117},{"id":"1710.10321","title":"Learning Structural Node Embeddings Via Diffusion Wavelets","created":"2017-10-27","cited_by_count":97},{"id":"2110.13987","title":"Learning Collaborative Policies to Solve NP-hard Routing Problems","created":"2021-10-26","cited_by_count":86},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"1809.02121","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","created":"2018-09-06","cited_by_count":77},{"id":"1803.07055","title":"Simple random search provides a competitive approach to reinforcement learning","created":"2018-03-19","cited_by_count":75},{"id":"1408.2701","title":"Epidemic processes in complex networks","created":"2014-08-12","cited_by_count":58},{"id":"2105.06631","title":"Ordering-Based Causal Discovery with Reinforcement Learning","created":"2021-05-14","cited_by_count":55},{"id":"2203.15544","title":"Graph Neural Networks are Dynamic Programmers","created":"2022-03-29","cited_by_count":55},{"id":"2006.09607","title":"Learning What to Defer for Maximum Independent Sets","created":"2020-06-17","cited_by_count":54},{"id":"1904.03177","title":"Structured agents for physical construction","created":"2019-04-05","cited_by_count":50},{"id":"2205.14210","title":"MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solvers","created":"2022-05-27","cited_by_count":49},{"id":"1806.01203","title":"Relational inductive bias for physical construction in humans and machines","created":"2018-06-04","cited_by_count":44},{"id":"1801.05757","title":"Experience-driven Networking: A Deep Reinforcement Learning based Approach","created":"2018-01-17","cited_by_count":41},{"id":"2201.10494","title":"What's Wrong with Deep Learning in Tree Search for Combinatorial Optimization","created":"2022-01-25","cited_by_count":37},{"id":"2303.15027","title":"A Survey on Causal Discovery Methods for I.I.D. and Time Series Data","created":"2023-03-27","cited_by_count":35},{"id":"1707.03034","title":"Learning Heuristic Search via Imitation","created":"2017-07-10","cited_by_count":34},{"id":"1802.04394","title":"M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search","created":"2018-02-12","cited_by_count":34},{"id":"2010.05313","title":"Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks","created":"2020-10-11","cited_by_count":30},{"id":"1807.01672","title":"Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization","created":"2018-07-04","cited_by_count":27},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21},{"id":"2311.14156","title":"Variational Annealing on Graphs for Combinatorial Optimization","created":"2023-11-23","cited_by_count":21},{"id":"1805.07440","title":"Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search","created":"2018-05-18","cited_by_count":18},{"id":"2112.12876","title":"Learning to Walk with Dual Agents for Knowledge Graph Reasoning","created":"2021-12-23","cited_by_count":16},{"id":"2001.11279","title":"Goal-directed graph construction using reinforcement learning","created":"2020-01-30","cited_by_count":14},{"id":"1710.11583","title":"Why (and How) Networks Should Run Themselves","created":"2017-10-31","cited_by_count":13},{"id":"2106.07039","title":"Contingency-Aware Influence Maximization: A Reinforcement Learning Approach","created":"2021-06-13","cited_by_count":13},{"id":"2303.05518","title":"Computably Continuous Reinforcement-Learning Objectives are PAC-learnable","created":"2023-03-09","cited_by_count":13},{"id":"2004.11986","title":"CFR-RL: Traffic Engineering with Reinforcement Learning in SDN","created":"2020-04-24","cited_by_count":12},{"id":"2107.07493","title":"Algorithmic Concept-based Explainable Reasoning","created":"2021-07-15","cited_by_count":12},{"id":"2009.12604","title":"Graph neural induction of value iteration","created":"2020-09-26","cited_by_count":9},{"id":"2104.09919","title":"GDDR: GNN-based Data-Driven Routing","created":"2021-04-20","cited_by_count":9},{"id":"2007.03619","title":"GraphOpt: Learning Optimization Models of Graph Formation","created":"2020-07-07","cited_by_count":7}],"next_cursor":"100"}