{"total":48,"rows":[{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111,"area":null},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2302.05981","title":"MarioGPT: Open-Ended Text2Level Generation through Large Language Models","created":"2023-02-12","cited_by_count":64,"area":null},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40,"area":null},{"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":"2106.15877","title":"Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2410.15644","title":"Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration","created":"2024-10-21","cited_by_count":22,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2305.06436","title":"Multi-Robot Coordination and Layout Design for Automated Warehousing","created":"2023-05-10","cited_by_count":17,"area":null},{"id":"2404.15538","title":"DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft","created":"2024-04-23","cited_by_count":17,"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":"2309.11975","title":"Inferring Capabilities from Task Performance with Bayesian Triangulation","created":"2023-09-21","cited_by_count":13,"area":null},{"id":"2310.18622","title":"Arbitrarily Scalable Environment Generators via Neural Cellular Automata","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2304.13787","title":"Surrogate Assisted Generation of Human-Robot Interaction Scenarios","created":"2023-04-26","cited_by_count":8,"area":null},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2405.16386","title":"Variational Offline Multi-agent Skill Discovery","created":"2024-05-26","cited_by_count":6,"area":null},{"id":"2402.01335","title":"BehAVE: Behaviour Alignment of Video Game Encodings","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2404.15192","title":"Measuring Diversity of Game Scenarios","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2103.15553","title":"Connectionism, Complexity, and Living Systems: a comparison of Artificial and Biological Neural Networks","created":"2021-03-15","cited_by_count":3,"area":null},{"id":"2107.12501","title":"Adversarial Random Forest Classifier for Automated Game Design","created":"2021-07-26","cited_by_count":3,"area":null},{"id":"2206.06424","title":"Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2211.06134","title":"Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2107.02991","title":"Keiki: Towards Realistic Danmaku Generation via Sequential GANs","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2207.02100","title":"Generating Game Levels of Diverse Behaviour Engagement","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2207.05991","title":"Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2305.00644","title":"Procedural Content Generation via Knowledge Transformation (PCG-KT)","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2309.15242","title":"PlotMap: Automated Layout Design for Building Game Worlds","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2107.07397","title":"Level generation and style enhancement -- deep learning for game development overview","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2305.18553","title":"Controllable Path of Destruction","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2411.13072","title":"AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2601.00105","title":"Mortar: Evolving Mechanics for Automatic Game Design","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2108.02323","title":"Active Reinforcement Learning over MDPs","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2203.01075","title":"Reliable validation of Reinforcement Learning Benchmarks","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2306.04813","title":"Human in the Loop Novelty Generation","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2412.08950","title":"Predicting Quality of Video Gaming Experience Using Global-Scale Telemetry Data and Federated Learning","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2506.15737","title":"A Study of Hybrid and Evolutionary Metaheuristics for Single Hidden Layer Feedforward Neural Network Architecture","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2510.04498","title":"GenQuest: An LLM-based Text Adventure Game for Language Learners","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2608.05148","title":"Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}