{"list":"other","total":113,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1612.05424","title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks","created":"2016-12-16","cited_by_count":308},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2010.03978","title":"A Brief Review of Domain Adaptation","created":"2020-10-07","cited_by_count":288},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193},{"id":"2210.17366","title":"Guided Conditional Diffusion for Controllable Traffic Simulation","created":"2022-10-31","cited_by_count":190},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"2212.01322","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","created":"2022-12-02","cited_by_count":178},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"id":"2406.07394","title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","created":"2024-06-11","cited_by_count":158},{"id":"2303.05512","title":"PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification","created":"2023-03-09","cited_by_count":154},{"id":"1905.05717","title":"CoLight: Learning Network-level Cooperation for Traffic Signal Control","created":"2019-05-11","cited_by_count":138},{"id":"2010.09776","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","created":"2020-10-19","cited_by_count":121},{"id":"2011.07215","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","created":"2020-11-14","cited_by_count":121},{"id":"1905.05217","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","created":"2019-05-13","cited_by_count":115},{"id":"1710.03641","title":"Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments","created":"2017-10-10","cited_by_count":108},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"1909.04847","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","created":"2019-09-11","cited_by_count":94},{"id":"2006.09001","title":"RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real","created":"2020-06-16","cited_by_count":91},{"id":"2011.03807","title":"Sim-to-Real Transfer for Vision-and-Language Navigation","created":"2020-11-07","cited_by_count":89},{"id":"2204.09667","title":"Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments","created":"2022-04-20","cited_by_count":86},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"1904.08117","title":"A Survey on Traffic Signal Control Methods","created":"2019-04-17","cited_by_count":79},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2005.04078","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","created":"2020-05-08","cited_by_count":72},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"2502.03349","title":"Robust Autonomy Emerges from Self-Play","created":"2025-02-05","cited_by_count":67},{"id":"1808.00720","title":"RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising","created":"2018-08-02","cited_by_count":65},{"id":"2001.01046","title":"Adversarial-Learned Loss for Domain Adaptation","created":"2020-01-04","cited_by_count":65},{"id":"2010.02966","title":"Reinforcement Learning with Random Delays","created":"2020-10-06","cited_by_count":59},{"id":"2305.01263","title":"How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence","created":"2023-05-02","cited_by_count":58},{"id":"1711.06606","title":"Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training","created":"2017-11-17","cited_by_count":57},{"id":"2304.14369","title":"Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics","created":"2023-04-27","cited_by_count":57},{"id":"2309.04077","title":"SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments","created":"2023-09-08","cited_by_count":53},{"id":"2404.05695","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","created":"2024-04-08","cited_by_count":53},{"id":"2410.03645","title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","created":"2024-10-04","cited_by_count":52},{"id":"1611.01843","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","created":"2016-11-06","cited_by_count":47},{"id":"1908.03190","title":"NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data","created":"2019-08-08","cited_by_count":42},{"id":"1911.04074","title":"SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic","created":"2019-11-11","cited_by_count":40},{"id":"1710.06422","title":"Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation","created":"2017-10-17","cited_by_count":36},{"id":"2308.14284","title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","created":"2023-08-28","cited_by_count":36},{"id":"1802.00265","title":"VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control","created":"2018-02-01","cited_by_count":35},{"id":"2011.12421","title":"Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents","created":"2020-11-24","cited_by_count":35},{"id":"1908.03761","title":"Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning","created":"2019-08-10","cited_by_count":33},{"id":"2104.10584","title":"Deep Learning for Click-Through Rate Estimation","created":"2021-04-21","cited_by_count":33},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31},{"id":"2207.10821","title":"Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation","created":"2022-07-21","cited_by_count":30},{"id":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30},{"id":"1707.00051","title":"Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars","created":"2017-06-30","cited_by_count":28},{"id":"2401.10545","title":"Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency","created":"2024-01-19","cited_by_count":28},{"id":"1905.12767","title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","created":"2019-05-29","cited_by_count":27},{"id":"2210.14413","title":"InterSim: Interactive Traffic Simulation via Explicit Relation Modeling","created":"2022-10-26","cited_by_count":27},{"id":"1810.07286","title":"At Human Speed: Deep Reinforcement Learning with Action Delay","created":"2018-10-16","cited_by_count":26},{"id":"1912.06321","title":"Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?","created":"2019-12-13","cited_by_count":26},{"id":"2011.00038","title":"Waymo Public Road Safety Performance Data","created":"2020-10-30","cited_by_count":24},{"id":"1801.09271","title":"Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data","created":"2018-01-28","cited_by_count":23},{"id":"2407.00994","title":"LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation","created":"2024-07-01","cited_by_count":23},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22},{"id":"2008.06686","title":"Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics","created":"2020-08-15","cited_by_count":21},{"id":"2108.07555","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","created":"2021-08-17","cited_by_count":21},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21},{"id":"2405.10020","title":"Natural Language Can Help Bridge the Sim2Real Gap","created":"2024-05-16","cited_by_count":21},{"id":"2202.07133","title":"Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving","created":"2022-02-15","cited_by_count":20},{"id":"2305.10504","title":"Model-Free Robust Average-Reward Reinforcement Learning","created":"2023-05-17","cited_by_count":20},{"id":"2405.15460","title":"TD3 Based Collision Free Motion Planning for Robot Navigation","created":"2024-05-24","cited_by_count":20},{"id":"2002.09107","title":"Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras","created":"2020-02-21","cited_by_count":18},{"id":"2008.01279","title":"Reinforced Grounded Action Transformation for Sim-to-Real Transfer","created":"2020-08-04","cited_by_count":18},{"id":"1607.08665","title":"Introspective Perception: Learning to Predict Failures in Vision Systems","created":"2016-07-28","cited_by_count":17},{"id":"1703.00472","title":"Reinforcement Learning for Pivoting Task","created":"2017-03-01","cited_by_count":17},{"id":"2203.11653","title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","created":"2022-03-22","cited_by_count":17},{"id":"2306.15136","title":"What Truly Matters in Trajectory Prediction for Autonomous Driving?","created":"2023-06-27","cited_by_count":17},{"id":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17},{"id":"2008.01281","title":"Stochastic Grounded Action Transformation for Robot Learning in Simulation","created":"2020-08-04","cited_by_count":16},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16},{"id":"2412.05789","title":"InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction","created":"2024-12-08","cited_by_count":15}],"next_cursor":"100"}