{"total":522,"rows":[{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442,"area":null},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250,"area":null},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"area":null},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126,"area":null},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"area":null},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119,"area":null},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114,"area":null},{"id":"2304.00464","title":"UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning","created":"2023-04-02","cited_by_count":107,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2209.11178","title":"Poisson Flow Generative Models","created":"2022-09-22","cited_by_count":95,"area":null},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94,"area":null},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94,"area":null},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76,"area":null},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"area":null},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62,"area":null},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2205.03195","title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","created":"2022-05-06","cited_by_count":61,"area":null},{"id":"2104.03086","title":"Trajectory Prediction with Latent Belief Energy-Based Model","created":"2021-04-07","cited_by_count":60,"area":null},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60,"area":null},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52,"area":null},{"id":"2309.07907","title":"Physically Plausible Full-Body Hand-Object Interaction Synthesis","created":"2023-09-14","cited_by_count":52,"area":null},{"id":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51,"area":null},{"id":"2308.09036","title":"Synthesizing Physically Plausible Human Motions in 3D Scenes","created":"2023-08-17","cited_by_count":49,"area":null},{"id":"2301.13868","title":"PADL: Language-Directed Physics-Based Character Control","created":"2023-01-31","cited_by_count":48,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2111.07999","title":"Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization","created":"2021-11-15","cited_by_count":46,"area":null},{"id":"2103.09742","title":"Training GANs with Stronger Augmentations via Contrastive Discriminator","created":"2021-03-17","cited_by_count":45,"area":null},{"id":"2103.14666","title":"Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning","created":"2021-03-26","cited_by_count":45,"area":null},{"id":"2110.00675","title":"Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview","created":"2021-10-01","cited_by_count":45,"area":null},{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2203.02878","title":"A Survey for Solving Mixed Integer Programming via Machine Learning","created":"2022-03-06","cited_by_count":44,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2412.05334","title":"Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2102.11938","title":"Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others","created":"2021-02-23","cited_by_count":39,"area":null},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38,"area":null},{"id":"2305.03249","title":"PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors","created":"2023-05-05","cited_by_count":38,"area":null},{"id":"2308.07200","title":"Neural Categorical Priors for Physics-Based Character Control","created":"2023-08-14","cited_by_count":38,"area":null},{"id":"2203.14912","title":"Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning","created":"2022-03-23","cited_by_count":37,"area":null},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37,"area":null},{"id":"2308.15143","title":"Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models","created":"2023-08-29","cited_by_count":37,"area":null},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2512.01809","title":"Much Ado About Noising: Dispelling the Myths of Generative Robotic Control","created":"2025-12-01","cited_by_count":36,"area":null},{"id":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2310.16917","title":"MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation","created":"2023-10-25","cited_by_count":34,"area":null},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2305.15930","title":"End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes","created":"2023-05-25","cited_by_count":32,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2206.14349","title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","created":"2022-06-29","cited_by_count":30,"area":null},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2402.07369","title":"Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation","created":"2024-02-12","cited_by_count":29,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2305.03286","title":"Composite Motion Learning with Task Control","created":"2023-05-05","cited_by_count":28,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2304.06094","title":"Energy-guided Entropic Neural Optimal Transport","created":"2023-04-12","cited_by_count":26,"area":null},{"id":"2402.18587","title":"At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2402.14807","title":"A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health","created":"2024-02-22","cited_by_count":24,"area":null},{"id":"2502.10444","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","created":"2025-02-11","cited_by_count":24,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23,"area":null}],"next_cursor":"100"}