{"total":198,"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":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"area":null},{"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":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"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":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125,"area":"agents"},{"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":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2407.04363","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","created":"2024-07-05","cited_by_count":102,"area":"wm"},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"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":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"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":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2505.18134","title":"VideoGameBench: Can Vision-Language Models complete popular video games?","created":"2025-05-23","cited_by_count":36,"area":"mllm"},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33,"area":null},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33,"area":null},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"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":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2402.03244","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","created":"2024-02-05","cited_by_count":26,"area":null},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","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":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"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":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","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":"2211.15944","title":"The Effectiveness of World Models for Continual Reinforcement Learning","created":"2022-11-29","cited_by_count":17,"area":"wm"},{"id":"2403.00690","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","created":"2024-03-01","cited_by_count":17,"area":"agents"},{"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":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2503.04094","title":"Pok\\'eChamp: an Expert-level Minimax Language Agent","created":"2025-03-06","cited_by_count":16,"area":"agents"},{"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":"2205.04887","title":"Search-Based Testing of Reinforcement Learning","created":"2022-05-07","cited_by_count":13,"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":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"id":"2110.10661","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2307.09423","title":"Scaling Laws for Imitation Learning in Single-Agent Games","created":"2023-07-18","cited_by_count":11,"area":"agents"},{"id":"2410.23022","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","created":"2024-10-30","cited_by_count":10,"area":"agents"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"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":"2210.00066","title":"Improving Policy Learning via Language Dynamics Distillation","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2307.11922","title":"Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2311.03736","title":"Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9,"area":"agents"},{"id":"2407.17695","title":"Enhancing Agent Learning through World Dynamics Modeling","created":"2024-07-25","cited_by_count":9,"area":"agents"},{"id":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2508.08501","title":"GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2305.10865","title":"Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning","created":"2023-05-18","cited_by_count":8,"area":"agents"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2507.09177","title":"Continual Reinforcement Learning by Planning with Online World Models","created":"2025-07-12","cited_by_count":8,"area":"wm"},{"id":"2207.11584","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2304.00046","title":"Accelerating exploration and representation learning with offline pre-training","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2409.12798","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2410.15221","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","created":"2024-10-19","cited_by_count":7,"area":"driving"},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2012.02527","title":"Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments","created":"2020-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2312.07540","title":"diff History for Neural Language Agents","created":"2023-12-12","cited_by_count":6,"area":"agents"},{"id":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"}],"next_cursor":"100"}