{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"2302.14545","title":"Modern Bayesian Experimental Design","created":"2023-02-28","cited_by_count":125},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"2406.10759","title":"Humanoid Parkour Learning","created":"2024-06-15","cited_by_count":96},{"id":"1806.01316","title":"Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach","created":"2018-06-04","cited_by_count":91},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"1801.09667","title":"Information Directed Sampling and Bandits with Heteroscedastic Noise","created":"2018-01-29","cited_by_count":76},{"id":"1802.04412","title":"Efficient Exploration through Bayesian Deep Q-Networks","created":"2018-02-13","cited_by_count":67},{"id":"2311.17874","title":"FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information","created":"2023-11-29","cited_by_count":64},{"id":"1905.06125","title":"Distributional Reinforcement Learning for Efficient Exploration","created":"2019-05-13","cited_by_count":60},{"id":"2309.15462","title":"DTC: Deep Tracking Control","created":"2023-09-27","cited_by_count":56},{"id":"1812.07544","title":"Information-Directed Exploration for Deep Reinforcement Learning","created":"2018-12-18","cited_by_count":52},{"id":"2501.10100","title":"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics","created":"2025-01-17","cited_by_count":51},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49},{"id":"1611.01843","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","created":"2016-11-06","cited_by_count":47},{"id":"2404.12308","title":"ASID: Active Exploration for System Identification in Robotic Manipulation","created":"2024-04-18","cited_by_count":28},{"id":"1804.04012","title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","created":"2018-04-11","cited_by_count":27},{"id":"2601.22074","title":"mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning","created":"2026-01-29","cited_by_count":26},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24},{"id":"2102.05100","title":"On structural and practical identifiability","created":"2021-02-09","cited_by_count":19},{"id":"2504.21067","title":"GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction","created":"2025-04-29","cited_by_count":17},{"id":"1711.10789","title":"Efficient exploration with Double Uncertain Value Networks","created":"2017-11-29","cited_by_count":16},{"id":"2410.04680","title":"Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting","created":"2024-10-07","cited_by_count":10},{"id":"2505.14266","title":"Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning","created":"2025-05-20","cited_by_count":8},{"id":"2402.05872","title":"You've Got to Feel It To Believe It: Multi-Modal Bayesian Inference for Semantic and Property Prediction","created":"2024-02-08","cited_by_count":7},{"id":"2310.14968","title":"Bayesian Active Learning in the Presence of Nuisance Parameters","created":"2023-10-23","cited_by_count":6},{"id":"2410.10766","title":"Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain Navigation","created":"2024-10-14","cited_by_count":6},{"id":"2209.03210","title":"Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filter","created":"2022-09-07","cited_by_count":5},{"id":"2409.16228","title":"Fast Extrinsic Calibration for Multiple Inertial Measurement Units in Visual-Inertial System","created":"2024-09-24","cited_by_count":4},{"id":"2504.18471","title":"Action Flow Matching for Continual Robot Learning","created":"2025-04-25","cited_by_count":3},{"id":"2505.12214","title":"Behavior Synthesis via Contact-Aware Fisher Information Maximization","created":"2025-05-18","cited_by_count":2},{"id":"1709.03426","title":"Trajectory Synthesis for Fisher Information Maximization","created":"2017-09-11","cited_by_count":1},{"id":"2405.14440","title":"Bayesian Adaptive Calibration and Optimal Design","created":"2024-05-23","cited_by_count":1}],"next_cursor":null}