{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2208.06193","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","created":"2022-08-12","cited_by_count":562},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"2305.16381","title":"DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":450},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1710.04615","title":"Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation","created":"2017-10-12","cited_by_count":289},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263},{"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":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"1812.06298","title":"Residual Policy Learning","created":"2018-12-15","cited_by_count":164},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"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":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"1903.11239","title":"TossingBot: Learning to Throw Arbitrary Objects with Residual Physics","created":"2019-03-27","cited_by_count":137},{"id":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112},{"id":"1807.07814","title":"Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis","created":"2018-07-20","cited_by_count":110},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93},{"id":"2006.14616","title":"An Analysis of SVD for Deep Rotation Estimation","created":"2020-06-25","cited_by_count":86},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2301.13362","title":"Optimizing DDPM Sampling with Shortcut Fine-Tuning","created":"2023-01-31","cited_by_count":81},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75},{"id":"1911.07246","title":"IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks","created":"2019-11-17","cited_by_count":69},{"id":"1906.05841","title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","created":"2019-06-13","cited_by_count":64},{"id":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59},{"id":"2205.03532","title":"Factory: Fast Contact for Robotic Assembly","created":"2022-05-07","cited_by_count":54},{"id":"1905.01240","title":"Information asymmetry in KL-regularized RL","created":"2019-05-03","cited_by_count":53},{"id":"2305.17110","title":"IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality","created":"2023-05-26","cited_by_count":53},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49},{"id":"2111.05424","title":"AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale","created":"2021-11-09","cited_by_count":44},{"id":"2404.11735","title":"Learning with 3D rotations, a hitchhiker's guide to SO(3)","created":"2024-04-17","cited_by_count":42},{"id":"2404.03729","title":"JUICER: Data-Efficient Imitation Learning for Robotic Assembly","created":"2024-04-04","cited_by_count":38},{"id":"1808.03246","title":"Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing","created":"2018-08-09","cited_by_count":36},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31},{"id":"2008.07682","title":"Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation","created":"2020-08-18","cited_by_count":28},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23},{"id":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21},{"id":"2110.12618","title":"Learning Insertion Primitives with Discrete-Continuous Hybrid Action Space for Robotic Assembly Tasks","created":"2021-10-25","cited_by_count":20},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19},{"id":"2309.16909","title":"ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility","created":"2023-09-29","cited_by_count":18},{"id":"2104.14223","title":"InsertionNet -- A Scalable Solution for Insertion","created":"2021-04-29","cited_by_count":16},{"id":"1710.04102","title":"Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data","created":"2017-10-11","cited_by_count":10},{"id":"1509.04806","title":"A Framework for Fine Robotic Assembly","created":"2015-09-16","cited_by_count":8},{"id":"2203.03918","title":"Residual Robot Learning for Object-Centric Probabilistic Movement Primitives","created":"2022-03-08","cited_by_count":5}],"next_cursor":null}