{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","cited_by_count":652},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.02473","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","created":"2018-06-07","cited_by_count":364},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"2102.09548","title":"Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development","created":"2021-02-18","cited_by_count":264},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"1810.08678","title":"Optimization of Molecules via Deep Reinforcement Learning","created":"2018-10-19","cited_by_count":200},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"id":"2206.12411","title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","created":"2022-06-22","cited_by_count":155},{"id":"2110.14038","title":"Robustness of Graph Neural Networks at Scale","created":"2021-10-26","cited_by_count":100},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95},{"id":"2011.13230","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks","created":"2020-11-26","cited_by_count":94},{"id":"2204.00056","title":"SELFIES and the future of molecular string representations","created":"2022-03-31","cited_by_count":76},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"1912.05911","title":"Recurrent Neural Networks (RNNs): A gentle Introduction and Overview","created":"2019-11-23","cited_by_count":68},{"id":"2110.01219","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","created":"2021-10-04","cited_by_count":68},{"id":"2112.03041","title":"Keeping it Simple: Language Models can learn Complex Molecular Distributions","created":"2021-12-06","cited_by_count":68},{"id":"1810.03779","title":"Reinforcement Learning for Improving Agent Design","created":"2018-10-09","cited_by_count":56},{"id":"1801.01432","title":"Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning","created":"2018-01-04","cited_by_count":55},{"id":"2010.00979","title":"BOSS: Bayesian Optimization over String Spaces","created":"2020-10-02","cited_by_count":54},{"id":"1810.05751","title":"Policy Transfer with Strategy Optimization","created":"2018-10-12","cited_by_count":43},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42},{"id":"1911.06832","title":"Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning","created":"2019-11-15","cited_by_count":37},{"id":"1705.04612","title":"Molecular Generation with Recurrent Neural Networks (RNNs)","created":"2017-05-12","cited_by_count":36},{"id":"2108.10521","title":"Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study","created":"2021-08-24","cited_by_count":36},{"id":"1904.08547","title":"Deep Representation Learning for Social Network Analysis","created":"2019-04-18","cited_by_count":35},{"id":"2110.15486","title":"DOCKSTRING: easy molecular docking yields better benchmarks for ligand design","created":"2021-10-29","cited_by_count":35},{"id":"2211.13322","title":"Group SELFIES: A Robust Fragment-Based Molecular String Representation","created":"2022-11-23","cited_by_count":33},{"id":"2008.04460","title":"Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning","created":"2020-08-11","cited_by_count":32},{"id":"2106.04011","title":"JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design","created":"2021-06-07","cited_by_count":32},{"id":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29},{"id":"1708.08227","title":"ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?","created":"2017-08-28","cited_by_count":21},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21},{"id":"2012.09712","title":"Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations","created":"2020-12-17","cited_by_count":20},{"id":"1905.13343","title":"All SMILES Variational Autoencoder","created":"2019-05-30","cited_by_count":15},{"id":"2007.07298","title":"Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning","created":"2020-07-14","cited_by_count":7},{"id":"2106.07611","title":"Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization","created":"2021-06-14","cited_by_count":6},{"id":"2210.12458","title":"Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES","created":"2022-10-22","cited_by_count":5}],"next_cursor":null}