{"total":138,"rows":[{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747,"area":"wm"},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2312.03002","title":"The mechanistic basis of data dependence and abrupt learning in an in-context classification task","created":"2023-12-03","cited_by_count":118,"area":null},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111,"area":"agents"},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2310.10134","title":"CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization","created":"2023-10-16","cited_by_count":95,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70,"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":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2412.08442","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","created":"2024-12-11","cited_by_count":42,"area":"mllm"},{"id":"2301.13442","title":"Scaling laws for single-agent reinforcement learning","created":"2023-01-31","cited_by_count":41,"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":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"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":"2412.03782","title":"The broader spectrum of in-context learning","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"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":"2411.00986","title":"Taking AI Welfare Seriously","created":"2024-11-04","cited_by_count":31,"area":"agents"},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30,"area":"agents"},{"id":"2305.11598","title":"Introspective Tips: Large Language Model for In-Context Decision Making","created":"2023-05-19","cited_by_count":28,"area":null},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"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":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"area":"deeprl"},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2507.12821","title":"Assessing Adaptive World Models in Machines with Novel Games","created":"2025-07-17","cited_by_count":20,"area":"wm"},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2311.00344","title":"A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents","created":"2023-11-01","cited_by_count":18,"area":null},{"id":"2402.12284","title":"Refining Minimax Regret for Unsupervised Environment Design","created":"2024-02-19","cited_by_count":18,"area":"deeprl"},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","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":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16,"area":"offlinerl"},{"id":"2302.03067","title":"Memory-Based Meta-Learning on Non-Stationary Distributions","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2506.05109","title":"Truly Self-Improving Agents Require Intrinsic Metacognitive Learning","created":"2025-06-05","cited_by_count":15,"area":"synth"},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2312.03121","title":"Evaluating Agents using Social Choice Theory","created":"2023-12-05","cited_by_count":11,"area":"agents"},{"id":"2402.00262","title":"Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective","created":"2024-02-01","cited_by_count":11,"area":"agents"},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2409.06613","title":"DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots","created":"2024-09-10","cited_by_count":11,"area":"deeprl"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2506.14811","title":"Self-Composing Policies for Scalable Continual Reinforcement Learning","created":"2025-06-04","cited_by_count":11,"area":"deeprl"},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2311.12716","title":"minimax: Efficient Baselines for Autocurricula in JAX","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2410.01791","title":"DreamGarden: A Designer Assistant for Growing Games from a Single Prompt","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2410.19715","title":"Adversarial Environment Design via Regret-Guided Diffusion Models","created":"2024-10-25","cited_by_count":10,"area":"diffusion"},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2509.04575","title":"Bootstrapping Task Spaces for Self-Improvement","created":"2025-09-04","cited_by_count":10,"area":"synth"},{"id":"2307.11546","title":"Towards practical reinforcement learning for tokamak magnetic control","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2310.14526","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2403.02985","title":"Evolution Transformer: In-Context Evolutionary Optimization","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2406.00392","title":"Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning","created":"2024-06-01","cited_by_count":8,"area":"deeprl"},{"id":"2410.14086","title":"In-context learning and Occam's razor","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2411.05189","title":"Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens","created":"2024-11-07","cited_by_count":8,"area":null},{"id":"2404.17070","title":"Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey","created":"2024-04-25","cited_by_count":7,"area":"deeprl"},{"id":"2406.08002","title":"Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning","created":"2024-06-12","cited_by_count":7,"area":"deeprl"},{"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":"2410.02751","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","created":"2024-10-03","cited_by_count":7,"area":"deeprl"},{"id":"2511.00602","title":"OpenSIR: Open-Ended Self-Improving Reasoner","created":"2025-11-01","cited_by_count":7,"area":"lr"},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2403.15341","title":"Collaborative AI Teaming in Unknown Environments via Active Goal Deduction","created":"2024-03-22","cited_by_count":6,"area":null},{"id":"2404.12626","title":"Grasper: A Generalist Pursuer for Pursuit-Evasion Problems","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2505.17010","title":"Understanding Prompt Tuning and In-Context Learning via Meta-Learning","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2307.02276","title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2308.06668","title":"Large Language Models and Foundation Models in Smart Agriculture: Basics, Opportunities, and Challenges","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2405.01684","title":"Intelligent Switching for Reset-Free RL","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2509.00116","title":"Meta-learning ecological priors from large language models explains human learning and decision making","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2509.13341","title":"Imagined Autocurricula","created":"2025-09-11","cited_by_count":4,"area":"wm"},{"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":"2312.05822","title":"Toward Open-ended Embodied Tasks Solving","created":"2023-12-10","cited_by_count":3,"area":null},{"id":"2411.04466","title":"Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity","created":"2024-11-07","cited_by_count":3,"area":"deeprl"},{"id":"2411.13537","title":"Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)","created":"2024-11-20","cited_by_count":3,"area":"agents"},{"id":"2509.18389","title":"Towards Provable Emergence of In-Context Reinforcement Learning","created":"2025-09-22","cited_by_count":3,"area":"deeprl"},{"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":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2312.11414","title":"The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research","created":"2023-12-18","cited_by_count":2,"area":null}],"next_cursor":"100"}