{"total":111,"rows":[{"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":"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":"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":"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":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"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":"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":"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":"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":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2603.13372","title":"The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning","created":"2026-03-09","cited_by_count":6,"area":null},{"id":"2208.14928","title":"Cell-Free Latent Go-Explore","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2211.15414","title":"Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2607.01224","title":"AutoMem: Automated Learning of Memory as a Cognitive Skill","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2207.10218","title":"The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning","created":"2022-07-20","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":"2408.09386","title":"Game Development as Human-LLM Interaction","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2204.11350","title":"Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2205.13079","title":"Learning to Query Internet Text for Informing Reinforcement Learning Agents","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2404.00276","title":"Instruction-Driven Game Engines on Large Language Models","created":"2024-03-30","cited_by_count":3,"area":null},{"id":"2410.13441","title":"Instruction-Driven Game Engine: A Poker Case Study","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2511.01107","title":"SLAP: Shortcut Learning for Abstract Planning","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","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":"2110.08307","title":"GrowSpace: Learning How to Shape Plants","created":"2021-10-15","cited_by_count":2,"area":null},{"id":"2210.13942","title":"Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","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":"2307.03906","title":"ScriptWorld: Text Based Environment For Learning Procedural Knowledge","created":"2023-07-08","cited_by_count":2,"area":null},{"id":"2310.17537","title":"Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2507.05561","title":"Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2508.08382","title":"UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2209.04911","title":"Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space","created":"2022-09-11","cited_by_count":1,"area":null},{"id":"2306.13157","title":"Anticipatory Thinking Challenges in Open Worlds: Risk Management","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2308.15911","title":"Cyclophobic Reinforcement Learning","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2312.08463","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2411.16262","title":"Probing for Consciousness in Machines","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2412.06877","title":"The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2510.01531","title":"Information Seeking for Robust Decision Making under Partial Observability","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2604.08340","title":"Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2109.15147","title":"Reinforcement Learning with Information-Theoretic Actuation","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2203.10351","title":"The Sandbox Environment for Generalizable Agent Research (SEGAR)","created":"2022-03-19","cited_by_count":0,"area":null}],"next_cursor":"100"}