{"total":87,"rows":[{"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":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117,"area":null},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97,"area":null},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2102.09532","title":"Clockwork Variational Autoencoders","created":"2021-02-18","cited_by_count":42,"area":null},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"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":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2303.16563","title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","created":"2023-03-29","cited_by_count":36,"area":null},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35,"area":null},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2204.08373","title":"Learning to Execute Actions or Ask Clarification Questions","created":"2022-04-18","cited_by_count":30,"area":null},{"id":"2209.08483","title":"Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2202.10583","title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","created":"2022-02-17","cited_by_count":26,"area":null},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"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":"2312.08958","title":"LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2208.01174","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","created":"2022-08-01","cited_by_count":13,"area":null},{"id":"2412.18293","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2405.17424","title":"LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence","created":"2024-05-27","cited_by_count":10,"area":null},{"id":"2505.12707","title":"PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9,"area":null},{"id":"2503.02505","title":"ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2503.10684","title":"Open-World Skill Discovery from Unsegmented Demonstrations","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2312.12891","title":"MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2206.11736","title":"NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2407.03969","title":"Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2408.13934","title":"Learning to Move Like Professional Counter-Strike Players","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2312.15313","title":"Human-Centric Resource Allocation for the Metaverse With Multiaccess Edge Computing","created":"2023-12-23","cited_by_count":3,"area":null},{"id":"2508.15679","title":"An Efficient Open World Environment for Multi-Agent Social Learning","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2508.18708","title":"Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2106.03748","title":"Towards robust and domain agnostic reinforcement learning competitions","created":"2021-06-07","cited_by_count":2,"area":null},{"id":"2306.17766","title":"Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2307.12158","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2406.14343","title":"IWISDM: Assessing instruction following in multimodal models at scale","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2409.09455","title":"Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2409.18624","title":"Unsupervised Cognition","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2505.11962","title":"CrafText Benchmark: Advancing Instruction Following in Complex Multimodal Open-Ended World","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2104.08890","title":"Modular Procedural Generation for Voxel Maps","created":"2021-04-18","cited_by_count":1,"area":null},{"id":"2204.08687","title":"Many Episode Learning in a Modular Embodied Agent via End-to-End Interaction","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2212.13659","title":"Latent Discretization for Continuous-time Sequence Compression","created":"2022-12-28","cited_by_count":1,"area":null},{"id":"2406.03361","title":"What Matters in Hierarchical Search for Combinatorial Reasoning Problems?","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2407.08898","title":"IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2503.21263","title":"Cultivating Game Sense for Yourself: Making VLMs Gaming Experts","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2103.16732","title":"Simultaneous Navigation and Construction Benchmarking Environments","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2206.10720","title":"Predicting Team Performance with Spatial Temporal Graph Convolutional Networks","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2306.00975","title":"Active Vision Reinforcement Learning under Limited Visual Observability","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2307.06152","title":"Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions","created":"2023-07-12","cited_by_count":0,"area":null},{"id":"2310.07981","title":"Reinforcement Learning of Display Transfer Robots in Glass Flow Control Systems: A Physical Simulation-Based Approach","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2311.16172","title":"Evolutionary Machine Learning and Games","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2602.02306","title":"Spark: Modular Spiking Neural Networks","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.13131","title":"MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.00145","title":"Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.29577","title":"DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.25001","title":"GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.13829","title":"MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19257","title":"Long-horizon Video Generation with Slot Memory Addressed By Region Tokens","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}