{"total":1736,"rows":[{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006,"area":"agents"},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427,"area":"offlinerl"},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251,"area":"agents"},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766,"area":null},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492,"area":"offlinerl"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297,"area":null},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"area":null},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206,"area":"lr"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190,"area":"offlinerl"},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165,"area":null},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160,"area":"diffusion"},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136,"area":"deeprl"},{"id":"2310.10701","title":"Theory of Mind for Multi-Agent Collaboration via Large Language Models","created":"2023-10-16","cited_by_count":135,"area":"agents"},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133,"area":"offlinerl"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2109.06716","title":"HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO","created":"2021-09-14","cited_by_count":112,"area":null},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112,"area":null},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111,"area":null},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100,"area":"offlinerl"},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100,"area":"offlinerl"},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2202.08450","title":"Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization","created":"2022-02-17","cited_by_count":97,"area":null},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96,"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":"2510.11977","title":"Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation","created":"2025-10-13","cited_by_count":92,"area":"agents"},{"id":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"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":"2505.11409","title":"Visual Planning: Let's Think Only with Images","created":"2025-05-16","cited_by_count":85,"area":"lr"},{"id":"2502.03438","title":"BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving","created":"2025-02-05","cited_by_count":84,"area":null},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83,"area":null},{"id":"2205.13600","title":"MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control","created":"2022-05-26","cited_by_count":80,"area":null},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77,"area":null},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73,"area":"mllm"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"area":"offlinerl"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68,"area":null},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67,"area":"offlinerl"},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2106.13898","title":"Closed-form Continuous-time Neural Models","created":"2021-06-25","cited_by_count":65,"area":null},{"id":"2202.07008","title":"Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing","created":"2022-02-14","cited_by_count":64,"area":"driving"},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64,"area":null},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60,"area":"offlinerl"},{"id":"2104.07715","title":"Quantum Architecture Search via Deep Reinforcement Learning","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2102.06483","title":"Scalable Bayesian Inverse Reinforcement Learning","created":"2021-02-12","cited_by_count":56,"area":"offlinerl"},{"id":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56,"area":null},{"id":"2510.27492","title":"ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning","created":"2025-10-30","cited_by_count":56,"area":"lr"},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2006.14154","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","created":"2020-06-25","cited_by_count":54,"area":"offlinerl"},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"area":"offlinerl"},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52,"area":null},{"id":"2303.13367","title":"ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing","created":"2023-03-21","cited_by_count":52,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2109.00540","title":"Variational Quantum Reinforcement Learning via Evolutionary Optimization","created":"2021-09-01","cited_by_count":50,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2111.03062","title":"Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning","created":"2021-11-04","cited_by_count":50,"area":null},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49,"area":null},{"id":"2202.03825","title":"skrl: Modular and Flexible Library for Reinforcement Learning","created":"2022-02-08","cited_by_count":49,"area":null},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2201.09863","title":"Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots","created":"2022-01-24","cited_by_count":47,"area":null}],"next_cursor":"100"}