{"list":"other","total":67,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1809.02627","title":"Unity: A General Platform for Intelligent Agents","created":"2018-09-07","cited_by_count":236},{"id":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"1802.02871","title":"Online Learning: A Comprehensive Survey","created":"2018-02-08","cited_by_count":205},{"id":"1910.02509","title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting","created":"2019-10-06","cited_by_count":197},{"id":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"1809.05922","title":"Memory Efficient Experience Replay for Streaming Learning","created":"2018-09-16","cited_by_count":128},{"id":"2104.00405","title":"Avalanche: an End-to-End Library for Continual Learning","created":"2021-04-01","cited_by_count":124},{"id":"1810.13166","title":"Don't forget, there is more than forgetting: new metrics for Continual Learning","created":"2018-10-31","cited_by_count":115},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"1809.10635","title":"Generative replay with feedback connections as a general strategy for continual learning","created":"2018-09-27","cited_by_count":104},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"1909.01520","title":"Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis","created":"2019-09-04","cited_by_count":92},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38},{"id":"1912.05500","title":"What Can Learned Intrinsic Rewards Capture?","created":"2019-12-11","cited_by_count":36},{"id":"1904.02021","title":"Unsupervised Progressive Learning and the STAM Architecture","created":"2019-04-03","cited_by_count":30},{"id":"2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","created":"2020-07-14","cited_by_count":29},{"id":"2110.03331","title":"CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability","created":"2021-10-07","cited_by_count":28},{"id":"1904.06979","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","created":"2019-04-15","cited_by_count":27},{"id":"2010.02418","title":"The Effectiveness of Memory Replay in Large Scale Continual Learning","created":"2020-10-06","cited_by_count":26},{"id":"2112.02925","title":"Is Class-Incremental Enough for Continual Learning?","created":"2021-12-06","cited_by_count":22},{"id":"2104.08604","title":"Lifelong Learning with Sketched Structural Regularization","created":"2021-04-17","cited_by_count":15},{"id":"2201.07125","title":"WATCH: Wasserstein Change Point Detection for High-Dimensional Time Series Data","created":"2022-01-18","cited_by_count":13},{"id":"2201.08278","title":"Lifelong Learning Metrics","created":"2022-01-20","cited_by_count":13},{"id":"2109.14501","title":"Towards a theory of out-of-distribution learning","created":"2021-09-29","cited_by_count":11},{"id":"2111.00134","title":"Context Meta-Reinforcement Learning via Neuromodulation","created":"2021-10-30","cited_by_count":11},{"id":"2208.05056","title":"Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2","created":"2022-08-09","cited_by_count":11},{"id":"1509.03413","title":"Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets","created":"2015-09-11","cited_by_count":9},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6},{"id":"1909.09902","title":"Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture","created":"2019-09-21","cited_by_count":5},{"id":"2001.09822","title":"Uncertainty-based Modulation for Lifelong Learning","created":"2020-01-27","cited_by_count":5},{"id":"2007.06918","title":"Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer","created":"2020-07-14","cited_by_count":4},{"id":"2212.04603","title":"System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games","created":"2022-12-08","cited_by_count":3},{"id":"2006.11305","title":"Generalization of Agent Behavior through Explicit Representation of Context","created":"2020-06-18","cited_by_count":2},{"id":"2107.06686","title":"Safer Reinforcement Learning through Transferable Instinct Networks","created":"2021-07-14","cited_by_count":1},{"id":"2112.09670","title":"An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations","created":"2021-12-17","cited_by_count":1}],"next_cursor":null}