{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"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":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58},{"id":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","cited_by_count":54},{"id":"1612.06018","title":"Self-Correcting Models for Model-Based Reinforcement Learning","created":"2016-12-19","cited_by_count":43},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42},{"id":"2004.12974","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","created":"2020-04-27","cited_by_count":31},{"id":"1706.06544","title":"Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes","created":"2017-06-20","cited_by_count":29},{"id":"2309.14236","title":"MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation","created":"2023-09-25","cited_by_count":28},{"id":"2209.10788","title":"How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability","created":"2022-09-22","cited_by_count":27},{"id":"2002.03072","title":"Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials","created":"2020-02-08","cited_by_count":20},{"id":"2203.13429","title":"Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map","created":"2022-03-25","cited_by_count":20},{"id":"2102.09027","title":"Robust Model Predictive Path Integral Control: Analysis and Performance Guarantees","created":"2021-02-17","cited_by_count":17},{"id":"2208.07737","title":"Learning Efficient Abstract Planning Models that Choose What to Predict","created":"2022-08-16","cited_by_count":17},{"id":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16},{"id":"2312.04670","title":"Rapid Motor Adaptation for Robotic Manipulator Arms","created":"2023-12-07","cited_by_count":14},{"id":"2210.00153","title":"Probabilistic Traversability Model for Risk-Aware Motion Planning in Off-Road Environments","created":"2022-10-01","cited_by_count":13},{"id":"2207.07920","title":"Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features","created":"2022-07-16","cited_by_count":12},{"id":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10},{"id":"1609.07363","title":"Changepoint Detection in the Presence of Outliers","created":"2016-09-23","cited_by_count":9},{"id":"2304.01305","title":"PyFlyt -- UAV Simulation Environments for Reinforcement Learning Research","created":"2023-04-03","cited_by_count":9},{"id":"2111.11099","title":"Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot","created":"2021-11-22","cited_by_count":7},{"id":"2404.01596","title":"PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving","created":"2024-04-02","cited_by_count":7},{"id":"2410.10766","title":"Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain Navigation","created":"2024-10-14","cited_by_count":6},{"id":"1912.04201","title":"Learning Latent State Spaces for Planning through Reward Prediction","created":"2019-12-09","cited_by_count":4},{"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":"2111.08748","title":"Kernel-based diffusion approximated Markov decision processes for autonomous navigation and control on unstructured terrains","created":"2021-11-16","cited_by_count":3},{"id":"2207.05018","title":"Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning","created":"2022-07-11","cited_by_count":3},{"id":"2210.06605","title":"RAMP: A Risk-Aware Mapping and Planning Pipeline for Fast Off-Road Ground Robot Navigation","created":"2022-10-12","cited_by_count":3},{"id":"2402.13443","title":"Autonomous Mapless Navigation on Uneven Terrains","created":"2024-02-21","cited_by_count":3},{"id":"2403.19010","title":"Gaussian Process-based Traversability Analysis for Terrain Mapless Navigation","created":"2024-03-27","cited_by_count":3},{"id":"2404.03274","title":"Traversability-aware Adaptive Optimization for Path Planning and Control in Mountainous Terrain","created":"2024-04-04","cited_by_count":3},{"id":"2106.08531","title":"Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics","created":"2021-06-16","cited_by_count":2},{"id":"2001.10629","title":"Planning for the Unexpected: Explicitly Optimizing Motions for Ground Uncertainty in Running","created":"2020-01-28","cited_by_count":1},{"id":"2111.06742","title":"Self-Reflective Terrain-Aware Robot Adaptation for Consistent Off-Road Ground Navigation","created":"2021-11-12","cited_by_count":1},{"id":"2403.14956","title":"Boundary-Aware Value Function Generation for Safe Stochastic Motion Planning","created":"2024-03-22","cited_by_count":1}],"next_cursor":null}