{"list":"other","total":72,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2010.16011","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","created":"2020-10-30","cited_by_count":348},{"id":"1802.04240","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","created":"2018-02-12","cited_by_count":333},{"id":"1906.01227","title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","created":"2019-06-04","cited_by_count":269},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1912.02175","title":"Differentiation of Blackbox Combinatorial Solvers","created":"2019-12-04","cited_by_count":226},{"id":"2302.08224","title":"DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization","created":"2023-02-16","cited_by_count":221},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"1810.10659","title":"Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search","created":"2018-10-25","cited_by_count":183},{"id":"1912.05784","title":"Learning Improvement Heuristics for Solving Routing Problems","created":"2019-12-12","cited_by_count":164},{"id":"2012.10658","title":"Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances","created":"2020-12-19","cited_by_count":162},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"2010.12367","title":"Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning","created":"2020-10-23","cited_by_count":140},{"id":"2210.04123","title":"DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems","created":"2022-10-08","cited_by_count":129},{"id":"2012.10384","title":"Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* Neighborhood","created":"2020-11-23","cited_by_count":125},{"id":"2205.13209","title":"Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization","created":"2022-05-26","cited_by_count":119},{"id":"1911.09539","title":"Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem","created":"2019-11-21","cited_by_count":117},{"id":"2107.04139","title":"Learning to Delegate for Large-scale Vehicle Routing","created":"2021-07-08","cited_by_count":109},{"id":"2110.02544","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","created":"2021-10-06","cited_by_count":108},{"id":"2110.07983","title":"NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem","created":"2021-10-15","cited_by_count":103},{"id":"2004.01608","title":"Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning","created":"2020-04-03","cited_by_count":100},{"id":"2012.10638","title":"Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems","created":"2020-12-19","cited_by_count":100},{"id":"2106.05126","title":"Efficient Active Search for Combinatorial Optimization Problems","created":"2021-06-09","cited_by_count":100},{"id":"2102.11756","title":"Deep Policy Dynamic Programming for Vehicle Routing Problems","created":"2021-02-23","cited_by_count":94},{"id":"2106.11113","title":"Matrix Encoding Networks for Neural Combinatorial Optimization","created":"2021-06-21","cited_by_count":91},{"id":"2110.13987","title":"Learning Collaborative Policies to Solve NP-hard Routing Problems","created":"2021-10-26","cited_by_count":86},{"id":"2207.06190","title":"Simulation-guided Beam Search for Neural Combinatorial Optimization","created":"2022-07-13","cited_by_count":84},{"id":"1909.04063","title":"Exploratory Combinatorial Optimization with Reinforcement Learning","created":"2019-09-09","cited_by_count":82},{"id":"1911.04936","title":"Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning","created":"2019-11-12","cited_by_count":78},{"id":"2110.05291","title":"Graph Neural Network Guided Local Search for the Traveling Salesperson Problem","created":"2021-10-11","cited_by_count":70},{"id":"2210.07686","title":"Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation","created":"2022-10-14","cited_by_count":62},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"1712.09381","title":"RLlib: Abstractions for Distributed Reinforcement Learning","created":"2017-12-26","cited_by_count":54},{"id":"2006.09607","title":"Learning What to Defer for Maximum Independent Sets","created":"2020-06-17","cited_by_count":54},{"id":"2106.01086","title":"Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning","created":"2021-06-02","cited_by_count":52},{"id":"2007.04897","title":"Guiding Deep Molecular Optimization with Genetic Exploration","created":"2020-07-04","cited_by_count":51},{"id":"2304.09407","title":"Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem","created":"2023-04-19","cited_by_count":50},{"id":"2111.00234","title":"On Joint Learning for Solving Placement and Routing in Chip Design","created":"2021-10-30","cited_by_count":44},{"id":"2011.06069","title":"Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers","created":"2020-11-11","cited_by_count":43},{"id":"2006.03750","title":"Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time","created":"2020-06-06","cited_by_count":39},{"id":"2110.02634","title":"Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning","created":"2021-10-06","cited_by_count":36},{"id":"2202.07241","title":"Learning to Solve Routing Problems via Distributionally Robust Optimization","created":"2022-02-15","cited_by_count":31},{"id":"2204.11399","title":"Efficient Neural Neighborhood Search for Pickup and Delivery Problems","created":"2022-04-25","cited_by_count":29},{"id":"2206.00787","title":"On the Generalization of Neural Combinatorial Optimization Heuristics","created":"2022-06-01","cited_by_count":24},{"id":"1905.11623","title":"Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero","created":"2019-05-28","cited_by_count":23},{"id":"2306.02688","title":"Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization","created":"2023-06-05","cited_by_count":23},{"id":"1911.10641","title":"ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problems","created":"2019-11-24","cited_by_count":21},{"id":"1906.08809","title":"A Deep Reinforcement Learning Approach for Global Routing","created":"2019-06-20","cited_by_count":20},{"id":"2112.12545","title":"A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drone","created":"2021-12-22","cited_by_count":14},{"id":"2205.14105","title":"Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration","created":"2022-05-27","cited_by_count":14},{"id":"2207.05899","title":"Neural Topological Ordering for Computation Graphs","created":"2022-07-13","cited_by_count":12},{"id":"2205.13225","title":"DevFormer: A Symmetric Transformer for Context-Aware Device Placement","created":"2022-05-26","cited_by_count":11},{"id":"2110.03595","title":"Generalization in Deep RL for TSP Problems via Equivariance and Local Search","created":"2021-10-07","cited_by_count":9},{"id":"2303.13117","title":"RLOR: A Flexible Framework of Deep Reinforcement Learning for Operation Research","created":"2023-03-23","cited_by_count":4}],"next_cursor":null}