{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"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":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1905.07488","title":"Automatic Posterior Transformation for Likelihood-Free Inference","created":"2019-05-17","cited_by_count":219},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","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":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","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":"2406.10759","title":"Humanoid Parkour Learning","created":"2024-06-15","cited_by_count":96},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2011.04217","title":"NeuralSim: Augmenting Differentiable Simulators with Neural Networks","created":"2020-11-09","cited_by_count":82},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"2105.12244","title":"DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting","created":"2021-05-25","cited_by_count":64},{"id":"2403.07319","title":"Efficient Diffusion Model for Image Restoration by Residual Shifting","created":"2024-03-12","cited_by_count":64},{"id":"2309.15462","title":"DTC: Deep Tracking Control","created":"2023-09-27","cited_by_count":56},{"id":"2210.04872","title":"Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models","created":"2022-10-10","cited_by_count":50},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48},{"id":"2311.12085","title":"Pyramid Diffusion for Fine 3D Large Scene Generation","created":"2023-11-20","cited_by_count":44},{"id":"2302.11434","title":"iPlanner: Imperative Path Planning","created":"2023-02-22","cited_by_count":37},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32},{"id":"2406.12505","title":"Demonstrating Agile Flight from Pixels without State Estimation","created":"2024-06-18","cited_by_count":31},{"id":"2404.12308","title":"ASID: Active Exploration for System Identification in Robotic Manipulation","created":"2024-04-18","cited_by_count":28},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27},{"id":"2306.15864","title":"What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery","created":"2023-06-28","cited_by_count":27},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18},{"id":"2109.08815","title":"Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation","created":"2021-09-18","cited_by_count":17},{"id":"2405.00846","title":"Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination","created":"2024-05-01","cited_by_count":16},{"id":"2203.07322","title":"Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation","created":"2022-03-14","cited_by_count":14},{"id":"2405.12424","title":"Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers","created":"2024-05-21","cited_by_count":14},{"id":"2102.11003","title":"DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration","created":"2021-02-22","cited_by_count":11},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10},{"id":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10},{"id":"2210.04642","title":"Exploration via Planning for Information about the Optimal Trajectory","created":"2022-10-06","cited_by_count":8},{"id":"2401.08260","title":"Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms","created":"2024-01-16","cited_by_count":8},{"id":"2403.12193","title":"Continual Domain Randomization","created":"2024-03-18","cited_by_count":8},{"id":"2407.05425","title":"ClutterGen: A Cluttered Scene Generator for Robot Learning","created":"2024-07-07","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":"2311.07558","title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","created":"2023-11-13","cited_by_count":6},{"id":"2303.04136","title":"Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots","created":"2023-03-07","cited_by_count":2}],"next_cursor":null}