{"total":58,"rows":[{"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":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49,"area":null},{"id":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2103.14230","title":"Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2105.14074","title":"Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning","created":"2021-05-28","cited_by_count":43,"area":null},{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"1904.06317","title":"Few-Shot Bayesian Imitation Learning with Logical Program Policies","created":"2019-04-12","cited_by_count":30,"area":"offlinerl"},{"id":"2111.12990","title":"Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning","created":"2021-11-25","cited_by_count":27,"area":null},{"id":"2203.09250","title":"Symmetry-Based Representations for Artificial and Biological General Intelligence","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26,"area":"wm"},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2503.20124","title":"Synthesizing world models for bilevel planning","created":"2025-03-26","cited_by_count":14,"area":"wm"},{"id":"2210.08973","title":"FAIR for AI: An interdisciplinary and international community building perspective","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2107.13668","title":"Discovering User-Interpretable Capabilities of Black-Box Planning Agents","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"1808.07903","title":"LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations","created":"2018-08-23","cited_by_count":8,"area":"offlinerl"},{"id":"2303.05069","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2607.01531","title":"OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3","created":"2026-07-01","cited_by_count":8,"area":"wm"},{"id":"2303.05501","title":"PDSketch: Integrated Planning Domain Programming and Learning","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2210.07802","title":"Object-Category Aware Reinforcement Learning","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2301.10289","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","created":"2023-01-24","cited_by_count":3,"area":null},{"id":"2309.03483","title":"DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2106.05607","title":"Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2302.13240","title":"Q-Cogni: An Integrated Causal Reinforcement Learning Framework","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","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":"2602.24235","title":"SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2107.06015","title":"A Classification of Artificial Intelligence Systems for Mathematics Education","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2302.05448","title":"The Construction of Reality in an AI: A Review","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2306.05727","title":"The Role of Diverse Replay for Generalisation in Reinforcement Learning","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2409.13886","title":"Learning to Play Video Games with Intuitive Physics Priors","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2505.16581","title":"How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning","created":"2025-05-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2104.01980","title":"Probabilistic Programming Bots in Intuitive Physics Game Play","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2108.08960","title":"Plug and Play, Model-Based Reinforcement Learning","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2112.08369","title":"Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2203.10614","title":"Does DQN really learn? Exploring adversarial training schemes in Pong","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2211.03281","title":"Reward-Predictive Clustering","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2212.08626","title":"Hippocampus-Inspired Cognitive Architecture (HICA) for Operant Conditioning","created":"2022-12-16","cited_by_count":0,"area":null},{"id":"2401.09011","title":"Inductive Models for Artificial Intelligence Systems are Insufficient without Good Explanations","created":"2024-01-17","cited_by_count":0,"area":null},{"id":"2406.08069","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","created":"2024-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2407.14681","title":"Value Internalization: Learning and Generalizing from Social Reward","created":"2024-07-19","cited_by_count":0,"area":"alignment"},{"id":"2607.02846","title":"Object-Centric Environment Modeling for Agentic Tasks","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2609.31016","title":"Robust Successor Features","created":"2026-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2610.13172","title":"RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions","created":"2026-10-09","cited_by_count":0,"area":"wm"}],"next_cursor":null}