{"list":"other","total":70,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1708.08987","title":"Deep Learning for Medical Image Analysis","created":"2017-08-17","cited_by_count":401},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"1611.01989","title":"DeepCoder: Learning to Write Programs","created":"2016-11-07","cited_by_count":149},{"id":"1703.07469","title":"RobustFill: Neural Program Learning under Noisy I/O","created":"2017-03-21","cited_by_count":126},{"id":"1511.08228","title":"Neural GPUs Learn Algorithms","created":"2015-11-25","cited_by_count":121},{"id":"2005.13799","title":"Explainable deep learning models in medical image analysis","created":"2020-05-28","cited_by_count":111},{"id":"1910.13616","title":"Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation","created":"2019-10-30","cited_by_count":103},{"id":"1511.06279","title":"Neural Programmer-Interpreters","created":"2015-11-19","cited_by_count":101},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"2005.10636","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","created":"2020-05-20","cited_by_count":94},{"id":"1906.04604","title":"Write, Execute, Assess: Program Synthesis with a REPL","created":"2019-06-09","cited_by_count":93},{"id":"1705.10702","title":"Cautious Model Predictive Control using Gaussian Process Regression","created":"2017-05-30","cited_by_count":91},{"id":"1611.01855","title":"Neuro-Symbolic Program Synthesis","created":"2016-11-06","cited_by_count":84},{"id":"1805.04276","title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","created":"2018-05-11","cited_by_count":84},{"id":"1712.07294","title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning","created":"2017-12-20","cited_by_count":77},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"2003.10769","title":"Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection","created":"2020-03-22","cited_by_count":46},{"id":"2106.11053","title":"Leveraging Language to Learn Program Abstractions and Search Heuristics","created":"2021-06-18","cited_by_count":45},{"id":"1807.07665","title":"Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies","created":"2018-07-19","cited_by_count":43},{"id":"2008.06622","title":"Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings","created":"2020-08-15","cited_by_count":42},{"id":"2106.15339","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","created":"2021-06-26","cited_by_count":41},{"id":"1907.07273","title":"An Inductive Synthesis Framework for Verifiable Reinforcement Learning","created":"2019-07-16","cited_by_count":39},{"id":"2006.08084","title":"Neural Execution Engines: Learning to Execute Subroutines","created":"2020-06-15","cited_by_count":36},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"2107.00101","title":"Latent Execution for Neural Program Synthesis","created":"2021-06-29","cited_by_count":35},{"id":"1511.04834","title":"Neural Programmer: Inducing Latent Programs with Gradient Descent","created":"2015-11-16","cited_by_count":34},{"id":"1605.06640","title":"Programming with a Differentiable Forth Interpreter","created":"2016-05-21","cited_by_count":33},{"id":"1611.02109","title":"Differentiable Programs with Neural Libraries","created":"2016-11-07","cited_by_count":30},{"id":"1904.06317","title":"Few-Shot Bayesian Imitation Learning with Logical Program Policies","created":"2019-04-12","cited_by_count":30},{"id":"1707.04742","title":"Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities","created":"2017-07-15","cited_by_count":26},{"id":"2011.01928","title":"Generalization to New Actions in Reinforcement Learning","created":"2020-11-03","cited_by_count":25},{"id":"1801.03526","title":"Neural Program Synthesis with Priority Queue Training","created":"2018-01-10","cited_by_count":24},{"id":"1710.04157","title":"Neural Program Meta-Induction","created":"2017-10-11","cited_by_count":23},{"id":"1711.07163","title":"Dynamic Neural Program Embedding for Program Repair","created":"2017-11-20","cited_by_count":23},{"id":"2010.11940","title":"Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments","created":"2020-10-22","cited_by_count":23},{"id":"1810.01791","title":"FixMiner: Mining Relevant Fix Patterns for Automated Program Repair","created":"2018-10-03","cited_by_count":22},{"id":"1812.02788","title":"Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs","created":"2018-12-06","cited_by_count":21},{"id":"2012.00377","title":"Latent Programmer: Discrete Latent Codes for Program Synthesis","created":"2020-12-01","cited_by_count":18},{"id":"2012.12964","title":"Representing Partial Programs with Blended Abstract Semantics","created":"2020-12-23","cited_by_count":14},{"id":"2007.03629","title":"Strong Generalization and Efficiency in Neural Programs","created":"2020-07-07","cited_by_count":12},{"id":"2107.00339","title":"Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding","created":"2021-07-01","cited_by_count":12},{"id":"1912.07670","title":"To Follow or not to Follow: Selective Imitation Learning from Observations","created":"2019-12-16","cited_by_count":10},{"id":"1902.10657","title":"From explanation to synthesis: Compositional program induction for learning from demonstration","created":"2019-02-27","cited_by_count":9},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8},{"id":"1802.02696","title":"Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction","created":"2018-02-08","cited_by_count":3}],"next_cursor":null}