{"list":"other","total":55,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"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":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1809.08835","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","created":"2018-09-24","cited_by_count":175},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"1609.07845","title":"Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning","created":"2016-09-26","cited_by_count":118},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"2103.05668","title":"Core Challenges of Social Robot Navigation: A Survey","created":"2021-03-09","cited_by_count":106},{"id":"2012.09812","title":"ViNG: Learning Open-World Navigation with Visual Goals","created":"2020-12-17","cited_by_count":80},{"id":"2306.01874","title":"SACSoN: Scalable Autonomous Control for Social Navigation","created":"2023-06-02","cited_by_count":61},{"id":"2202.11271","title":"ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints","created":"2022-02-23","cited_by_count":58},{"id":"1903.02749","title":"Deep Visual MPC-Policy Learning for Navigation","created":"2019-03-07","cited_by_count":56},{"id":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56},{"id":"1903.00445","title":"A Behavioral Approach to Visual Navigation with Graph Localization Networks","created":"2019-03-01","cited_by_count":40},{"id":"2011.04820","title":"Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning","created":"2020-11-09","cited_by_count":40},{"id":"2301.06512","title":"DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles","created":"2023-01-16","cited_by_count":37},{"id":"2210.07450","title":"ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation","created":"2022-10-14","cited_by_count":19},{"id":"2304.09831","title":"FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing","created":"2023-04-19","cited_by_count":17},{"id":"2107.11637","title":"Group-based Motion Prediction for Navigation in Crowded Environments","created":"2021-07-24","cited_by_count":15},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14},{"id":"2109.05084","title":"Winding Through: Crowd Navigation via Topological Invariance","created":"2021-09-10","cited_by_count":11},{"id":"2206.08487","title":"High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization","created":"2022-06-16","cited_by_count":11},{"id":"1811.05929","title":"A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance","created":"2018-11-14","cited_by_count":10},{"id":"2204.13237","title":"Spatio-Temporal Graph Localization Networks for Image-based Navigation","created":"2022-04-28","cited_by_count":10},{"id":"2210.00552","title":"Occlusion-Aware Crowd Navigation Using People as Sensors","created":"2022-10-02","cited_by_count":9},{"id":"2007.05616","title":"NaviGAN: A Generative Approach for Socially Compliant Navigation","created":"2020-07-10","cited_by_count":7},{"id":"2011.09438","title":"EWareNet: Emotion Aware Human Intent Prediction and Adaptive Spatial Profile Fusion for Social Robot Navigation","created":"2020-11-18","cited_by_count":6},{"id":"2003.09224","title":"Probabilistic Visual Navigation with Bidirectional Image Prediction","created":"2020-03-20","cited_by_count":4},{"id":"2110.10415","title":"Depth360: Self-supervised Learning for Monocular Depth Estimation using Learnable Camera Distortion Model","created":"2021-10-20","cited_by_count":4}],"next_cursor":null}