{"list":"other","total":51,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"1810.02274","title":"Episodic Curiosity through Reachability","created":"2018-10-04","cited_by_count":109},{"id":"1912.02877","title":"Training Agents using Upside-Down Reinforcement Learning","created":"2019-12-05","cited_by_count":107},{"id":"2011.08909","title":"C-Learning: Learning to Achieve Goals via Recursive Classification","created":"2020-11-17","cited_by_count":103},{"id":"2002.05700","title":"BADGR: An Autonomous Self-Supervised Learning-Based Navigation System","created":"2020-02-13","cited_by_count":102},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","cited_by_count":89},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"2012.09812","title":"ViNG: Learning Open-World Navigation with Visual Goals","created":"2020-12-17","cited_by_count":80},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1810.06544","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","created":"2018-10-15","cited_by_count":76},{"id":"1710.03937","title":"PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning","created":"2017-10-11","cited_by_count":69},{"id":"2011.12491","title":"World Model as a Graph: Learning Latent Landmarks for Planning","created":"2020-11-25","cited_by_count":69},{"id":"1806.07377","title":"Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation","created":"2018-05-31","cited_by_count":50},{"id":"2006.09367","title":"Semantic Curiosity for Active Visual Learning","created":"2020-06-16","cited_by_count":45},{"id":"1803.07551","title":"Meta Reinforcement Learning with Latent Variable Gaussian Processes","created":"2018-03-20","cited_by_count":44},{"id":"1910.11670","title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","created":"2019-10-23","cited_by_count":40},{"id":"1909.12329","title":"Scaling Local Control to Large-Scale Topological Navigation","created":"2019-09-26","cited_by_count":37},{"id":"1912.06088","title":"Learning to Reach Goals via Iterated Supervised Learning","created":"2019-12-12","cited_by_count":26},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"2002.12336","title":"Hallucinative Topological Memory for Zero-Shot Visual Planning","created":"2020-02-27","cited_by_count":25},{"id":"1910.14055","title":"Policy Continuation with Hindsight Inverse Dynamics","created":"2019-10-30","cited_by_count":22},{"id":"2103.08022","title":"Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation","created":"2021-03-14","cited_by_count":22},{"id":"1805.07206","title":"Approximate Bayesian inference in spatial environments","created":"2018-05-18","cited_by_count":8},{"id":"2005.04912","title":"Maximizing Information Gain in Partially Observable Environments via Prediction Reward","created":"2020-05-11","cited_by_count":6}],"next_cursor":null}