{"total":236,"rows":[{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407,"area":null},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228,"area":null},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143,"area":"wm"},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135,"area":null},{"id":"2110.05113","title":"Learning High-Speed Flight in the Wild","created":"2021-10-11","cited_by_count":128,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58,"area":null},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49,"area":"agents"},{"id":"2503.24278","title":"AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World","created":"2025-03-31","cited_by_count":48,"area":null},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2507.10672","title":"Vision Language Action Models in Robotic Manipulation: A Systematic Review","created":"2025-07-14","cited_by_count":38,"area":"vla"},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36,"area":null},{"id":"2103.04847","title":"Adversarial Reinforcement Learning for Procedural Content Generation","created":"2021-03-08","cited_by_count":36,"area":null},{"id":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","cited_by_count":33,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2104.12233","title":"The 5th AI City Challenge","created":"2021-04-25","cited_by_count":28,"area":null},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27,"area":"agents"},{"id":"2304.02163","title":"GINA-3D: Learning to Generate Implicit Neural Assets in the Wild","created":"2023-04-04","cited_by_count":25,"area":null},{"id":"2105.13962","title":"NViSII: A Scriptable Tool for Photorealistic Image Generation","created":"2021-05-28","cited_by_count":24,"area":null},{"id":"2104.02215","title":"When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes","created":"2021-04-06","cited_by_count":23,"area":null},{"id":"2204.10380","title":"The 6th AI City Challenge","created":"2022-04-21","cited_by_count":23,"area":null},{"id":"2208.10590","title":"A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperation","created":"2022-08-22","cited_by_count":21,"area":null},{"id":"2201.00248","title":"Transfer RL across Observation Feature Spaces via Model-Based Regularization","created":"2022-01-01","cited_by_count":18,"area":null},{"id":"2211.09960","title":"Ask4Help: Learning to Leverage an Expert for Embodied Tasks","created":"2022-11-18","cited_by_count":18,"area":null},{"id":"2110.07594","title":"The Neural MMO Platform for Massively Multiagent Research","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2201.07833","title":"Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections","created":"2022-01-19","cited_by_count":16,"area":"driving"},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2203.11096","title":"CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2406.15149","title":"Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks","created":"2024-06-21","cited_by_count":14,"area":null},{"id":"2106.05864","title":"Verifiable and Compositional Reinforcement Learning Systems","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2301.07799","title":"A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems","created":"2023-01-18","cited_by_count":13,"area":null},{"id":"2309.11975","title":"Inferring Capabilities from Task Performance with Bayesian Triangulation","created":"2023-09-21","cited_by_count":13,"area":null},{"id":"2311.01267","title":"UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2112.12490","title":"Curriculum Learning for Safe Mapless Navigation","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2206.09603","title":"Constrained Reinforcement Learning for Robotics via Scenario-Based Programming","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2211.17188","title":"Automated Play-Testing Through RL Based Human-Like Play-Styles Generation","created":"2022-11-29","cited_by_count":11,"area":null},{"id":"2303.02160","title":"Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2312.05019","title":"Vision-based Learning for Drones: A Survey","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2408.00170","title":"CREW: Facilitating Human-AI Teaming Research","created":"2024-07-31","cited_by_count":11,"area":null},{"id":"2505.20294","title":"GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2111.05992","title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2205.11104","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2212.05241","title":"AutoDRIVE: A Comprehensive, Flexible and Integrated Digital Twin Ecosystem for Enhancing Autonomous Driving Research and Education","created":"2022-12-10","cited_by_count":10,"area":"driving"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2202.14034","title":"Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2204.12181","title":"Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach","created":"2022-04-26","cited_by_count":9,"area":null},{"id":"2209.00128","title":"Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata","created":"2022-08-31","cited_by_count":9,"area":null},{"id":"2210.14721","title":"Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data","created":"2022-10-25","cited_by_count":9,"area":"driving"},{"id":"2304.03443","title":"Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2502.17775","title":"FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks","created":"2025-02-25","cited_by_count":9,"area":"lr"},{"id":"2208.07123","title":"Online 3D Bin Packing Reinforcement Learning Solution with Buffer","created":"2022-08-15","cited_by_count":8,"area":null},{"id":"2304.00793","title":"FinnWoodlands Dataset","created":"2023-04-03","cited_by_count":8,"area":null},{"id":"2309.16347","title":"Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks","created":"2023-09-28","cited_by_count":8,"area":null},{"id":"2312.09906","title":"Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2105.01799","title":"Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction","created":"2021-05-04","cited_by_count":7,"area":null},{"id":"2307.01676","title":"RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games","created":"2023-07-04","cited_by_count":7,"area":null},{"id":"2308.00331","title":"Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning","created":"2023-08-01","cited_by_count":7,"area":null},{"id":"2105.04488","title":"A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2105.05145","title":"Visual Perspective Taking for Opponent Behavior Modeling","created":"2021-05-11","cited_by_count":6,"area":null},{"id":"2109.02529","title":"ViSTA: a Framework for Virtual Scenario-based Testing of Autonomous Vehicles","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2112.13595","title":"Depth estimation of endoscopy using sim-to-real transfer","created":"2021-12-27","cited_by_count":6,"area":null},{"id":"2202.12884","title":"Learning to Identify Perceptual Bugs in 3D Video Games","created":"2022-02-25","cited_by_count":6,"area":null},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2306.17101","title":"Identifying Important Sensory Feedback for Learning Locomotion Skills","created":"2023-06-29","cited_by_count":6,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2201.09463","title":"Cyber Mobility Mirror for Enabling Cooperative Driving Automation in Mixed Traffic: A Co-Simulation Platform","created":"2022-01-24","cited_by_count":5,"area":null},{"id":"2209.05559","title":"Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting","created":"2022-09-12","cited_by_count":5,"area":null},{"id":"2209.05661","title":"Unsupervised representation learning with recognition-parametrised probabilistic models","created":"2022-09-13","cited_by_count":5,"area":null},{"id":"2209.11294","title":"T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2303.05584","title":"SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2411.11761","title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","created":"2024-11-18","cited_by_count":5,"area":"agents"},{"id":"2106.03833","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","created":"2021-06-07","cited_by_count":4,"area":"offlinerl"},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2112.06106","title":"Controlled-rearing studies of newborn chicks and deep neural networks","created":"2021-12-12","cited_by_count":4,"area":null},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2209.12427","title":"Learning Continuous Control Policies for Information-Theoretic Active Perception","created":"2022-09-26","cited_by_count":4,"area":null},{"id":"2210.05845","title":"Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2210.10595","title":"DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2309.09476","title":"Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2309.15484","title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2412.00592","title":"LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes","created":"2024-11-30","cited_by_count":4,"area":"wm"},{"id":"2504.00234","title":"CBIL: Collective Behavior Imitation Learning for Fish from Real Videos","created":"2025-03-31","cited_by_count":4,"area":"offlinerl"},{"id":"2509.26161","title":"90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2512.04770","title":"Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2601.05899","title":"TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents","created":"2026-01-09","cited_by_count":4,"area":"agents"}],"next_cursor":"100"}