{"list":"other","total":72,"rows":[{"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"1904.00370","title":"Variational Adversarial Active Learning","created":"2019-03-31","cited_by_count":284},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122},{"id":"2007.04976","title":"One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control","created":"2020-07-09","cited_by_count":121},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111},{"id":"1703.01703","title":"Third-Person Imitation Learning","created":"2017-03-06","cited_by_count":103},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"1911.09162","title":"Deep Active Learning: Unified and Principled Method for Query and Training","created":"2019-11-20","cited_by_count":93},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2108.09331","title":"Influence Selection for Active Learning","created":"2021-08-20","cited_by_count":84},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77},{"id":"2104.02324","title":"Multiple instance active learning for object detection","created":"2021-04-06","cited_by_count":77},{"id":"1806.05473","title":"Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network","created":"2018-06-14","cited_by_count":74},{"id":"1702.07956","title":"Generative Adversarial Active Learning","created":"2017-02-25","cited_by_count":70},{"id":"1908.02144","title":"Bayesian Batch Active Learning as Sparse Subset Approximation","created":"2019-08-06","cited_by_count":68},{"id":"2301.08556","title":"NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis","created":"2023-01-18","cited_by_count":57},{"id":"2002.06583","title":"Reinforced active learning for image segmentation","created":"2020-02-16","cited_by_count":56},{"id":"2002.09564","title":"Towards Robust and Reproducible Active Learning Using Neural Networks","created":"2020-02-21","cited_by_count":54},{"id":"1912.00915","title":"Just Ask:An Interactive Learning Framework for Vision and Language Navigation","created":"2019-12-02","cited_by_count":53},{"id":"1808.06671","title":"Adversarial Sampling for Active Learning","created":"2018-08-20","cited_by_count":51},{"id":"2003.08165","title":"Neuroevolution of Self-Interpretable Agents","created":"2020-03-18","cited_by_count":49},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44},{"id":"1912.05361","title":"Parting with Illusions about Deep Active Learning","created":"2019-12-11","cited_by_count":38},{"id":"2303.14382","title":"Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm","created":"2023-03-25","cited_by_count":36},{"id":"1808.00928","title":"Learning Actionable Representations from Visual Observations","created":"2018-08-02","cited_by_count":35},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32},{"id":"1512.01693","title":"Deep Attention Recurrent Q-Network","created":"2015-12-05","cited_by_count":27},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27},{"id":"1810.10593","title":"Inverse reinforcement learning for video games","created":"2018-10-24","cited_by_count":26},{"id":"1811.08067","title":"Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions","created":"2018-11-20","cited_by_count":25},{"id":"2003.11249","title":"VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning","created":"2020-03-25","cited_by_count":25},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24},{"id":"2108.01069","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","created":"2021-08-02","cited_by_count":23},{"id":"1811.01292","title":"Geometry-Aware Recurrent Neural Networks for Active Visual Recognition","created":"2018-11-03","cited_by_count":20},{"id":"2011.06709","title":"Active Reinforcement Learning: Observing Rewards at a Cost","created":"2020-11-13","cited_by_count":20},{"id":"2012.09503","title":"Embodied Visual Active Learning for Semantic Segmentation","created":"2020-12-17","cited_by_count":19},{"id":"1605.00164","title":"Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion","created":"2016-04-30","cited_by_count":18},{"id":"2010.15942","title":"Machine versus Human Attention in Deep Reinforcement Learning Tasks","created":"2020-10-29","cited_by_count":16},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","cited_by_count":13},{"id":"2012.01227","title":"Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning","created":"2020-12-02","cited_by_count":4},{"id":"2006.11453","title":"Towards Adaptive Benthic Habitat Mapping","created":"2020-06-20","cited_by_count":3},{"id":"2010.13108","title":"Active and Interactive Mapping with Dynamic Gaussian Process Implicit Surfaces for Mobile Manipulators","created":"2020-10-25","cited_by_count":2},{"id":"1907.03116","title":"Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization","created":"2019-07-06","cited_by_count":1}],"next_cursor":null}