{"total":58,"rows":[{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2105.05330","title":"Neuro-Symbolic Artificial Intelligence: Current Trends","created":"2021-05-11","cited_by_count":54,"area":null},{"id":"2203.09634","title":"Predicate Invention for Bilevel Planning","created":"2022-03-17","cited_by_count":49,"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":"2301.05832","title":"World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges","created":"2023-01-14","cited_by_count":36,"area":"wm"},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35,"area":null},{"id":"2106.13229","title":"Model-Based Reinforcement Learning via Latent-Space Collocation","created":"2021-06-24","cited_by_count":28,"area":null},{"id":"2107.00110","title":"Classical Planning in Deep Latent Space","created":"2021-06-30","cited_by_count":22,"area":null},{"id":"2108.11204","title":"Subgoal Search For Complex Reasoning Tasks","created":"2021-08-25","cited_by_count":21,"area":null},{"id":"2208.07737","title":"Learning Efficient Abstract Planning Models that Choose What to Predict","created":"2022-08-16","cited_by_count":17,"area":null},{"id":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14,"area":"lr"},{"id":"2204.08479","title":"Inductive Biases for Object-Centric Representations in the Presence of Complex Textures","created":"2022-04-18","cited_by_count":13,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2501.00296","title":"From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models","created":"2024-12-31","cited_by_count":11,"area":"wm"},{"id":"2106.07487","title":"pix2rule: End-to-end Neuro-symbolic Rule Learning","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2203.02583","title":"Online Learning of Reusable Abstract Models for Object Goal Navigation","created":"2022-03-04","cited_by_count":9,"area":null},{"id":"1907.13627","title":"Disentangled Relational Representations for Explaining and Learning from Demonstration","created":"2019-07-31","cited_by_count":8,"area":"offlinerl"},{"id":"2411.14995","title":"Learning Lifted STRIPS Models from Action Traces Alone: A Simple, General, and Scalable Solution","created":"2024-11-22","cited_by_count":8,"area":null},{"id":"2112.01918","title":"Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning","created":"2021-12-03","cited_by_count":6,"area":null},{"id":"2312.12891","title":"MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2110.06149","title":"Planning from Pixels in Environments with Combinatorially Hard Search Spaces","created":"2021-10-12","cited_by_count":5,"area":null},{"id":"2407.16220","title":"ODGR: Online Dynamic Goal Recognition","created":"2024-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2106.05387","title":"Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2406.15850","title":"Learning Abstract World Model for Value-preserving Planning with Options","created":"2024-06-22","cited_by_count":4,"area":"wm"},{"id":"2503.21406","title":"Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning","created":"2025-03-27","cited_by_count":4,"area":"offlinerl"},{"id":"2207.05018","title":"Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning","created":"2022-07-11","cited_by_count":3,"area":null},{"id":"2309.00889","title":"Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers","created":"2023-09-02","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":"2604.19043","title":"Learning Lifted Action Models from Unsupervised Visual Traces","created":"2026-04-21","cited_by_count":3,"area":null},{"id":"2106.10354","title":"High-level Features for Resource Economy and Fast Learning in Skill Transfer","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2204.11902","title":"Learning First-Order Symbolic Planning Representations That Are Grounded","created":"2022-04-25","cited_by_count":2,"area":null},{"id":"2308.04867","title":"Learning Type-Generalized Actions for Symbolic Planning","created":"2023-08-09","cited_by_count":2,"area":null},{"id":"2508.21449","title":"Learning Lifted Action Models From Traces of Incomplete Actions and States","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2512.08411","title":"Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems","created":"2025-12-09","cited_by_count":2,"area":"wm"},{"id":"2108.09586","title":"Learning Causal Models of Autonomous Agents using Interventions","created":"2021-08-21","cited_by_count":1,"area":null},{"id":"2109.15310","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","created":"2021-09-30","cited_by_count":1,"area":null},{"id":"2206.03027","title":"Learning Symbolic Operators: A Neurosymbolic Solution for Autonomous Disassembly of Electric Vehicle Battery","created":"2022-06-07","cited_by_count":1,"area":null},{"id":"2211.15666","title":"Learning Visual Planning Models from Partially Observed Images","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2301.06054","title":"Planning for Learning Object Properties","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2307.03853","title":"Teach Me How to Learn: A Perspective Review towards User-centered Neuro-symbolic Learning for Robotic Surgical Systems","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2404.07826","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2502.13006","title":"Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks","created":"2025-02-18","cited_by_count":1,"area":"offlinerl"},{"id":"2207.05259","title":"Language-Based Causal Representation Learning","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2211.15589","title":"Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2306.11434","title":"Plausibility-Based Heuristics for Latent Space Classical Planning","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2309.05787","title":"Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2404.07934","title":"Goal Recognition via Linear Programming","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2409.11756","title":"Synthesizing Evolving Symbolic Representations for Autonomous Systems","created":"2024-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2410.21403","title":"Unveiling the Role of Expert Guidance: A Comparative Analysis of User-centered Imitation Learning and Traditional Reinforcement Learning","created":"2024-10-28","cited_by_count":0,"area":"offlinerl"},{"id":"2505.13372","title":"Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2602.04557","title":"Textual Planning with Explicit Latent Transitions","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.08685","title":"RAMP: Hybrid DRL for Online Learning of Numeric Action Models","created":"2026-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.02603","title":"Counterfactual Reasoning in Automated Planning","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.07736","title":"Online Goal Recognition using Path Signature and Dynamic Time Warping","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.13282","title":"Differentiable Learning of Lifted Action Schemas for Classical Planning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.15975","title":"Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning","created":"2026-05-15","cited_by_count":0,"area":"wm"},{"id":"2605.18627","title":"Learning Lifted Action Models from Traces with Minimal Information About Actions and States","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2609.16056","title":"Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}