{"total":36,"rows":[{"id":"2301.03313","title":"BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization","created":"2023-01-09","cited_by_count":82,"area":null},{"id":"2109.10129","title":"Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits","created":"2021-09-21","cited_by_count":38,"area":null},{"id":"2105.10830","title":"Learning First-Order Representations for Planning from Black-Box States: New Results","created":"2021-05-23","cited_by_count":23,"area":null},{"id":"2107.07076","title":"An Overview and Experimental Study of Learning-based Optimization Algorithms for Vehicle Routing Problem","created":"2021-07-15","cited_by_count":22,"area":null},{"id":"2205.06002","title":"Learning Generalized Policies Without Supervision Using GNNs","created":"2022-05-12","cited_by_count":22,"area":null},{"id":"2403.16508","title":"Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2112.03386","title":"Guided Imitation of Task and Motion Planning","created":"2021-12-06","cited_by_count":18,"area":null},{"id":"2203.14852","title":"Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width: Extended Version","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2101.02647","title":"From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation","created":"2021-01-07","cited_by_count":11,"area":null},{"id":"2110.00898","title":"A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2204.10420","title":"PG3: Policy-Guided Planning for Generalized Policy Generation","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2101.00692","title":"Learning General Policies from Small Examples Without Supervision","created":"2021-01-03","cited_by_count":7,"area":null},{"id":"2204.12665","title":"Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems","created":"2022-04-27","cited_by_count":7,"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":"2301.11087","title":"Generalized Planning as Heuristic Search: A new planning search-space that leverages pointers over objects","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2311.05490","title":"General Policies, Subgoal Structure, and Planning Width","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2104.10535","title":"Exploiting Learned Policies in Focal Search","created":"2021-04-21","cited_by_count":3,"area":null},{"id":"2505.00439","title":"Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2102.04518","title":"A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2107.02603","title":"Meta-Reinforcement Learning for Heuristic Planning","created":"2021-07-06","cited_by_count":2,"area":null},{"id":"2203.00669","title":"Hierarchical Reinforcement Learning with AI Planning Models","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2203.12679","title":"Sample-efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2204.04301","title":"Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems","created":"2022-04-08","cited_by_count":2,"area":null},{"id":"2209.05206","title":"A Differentiable Loss Function for Learning Heuristics in A*","created":"2022-09-12","cited_by_count":2,"area":null},{"id":"2210.05393","title":"Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2306.04019","title":"Learning Search-Space Specific Heuristics Using Neural Networks","created":"2023-06-06","cited_by_count":2,"area":null},{"id":"2508.18515","title":"Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2403.16824","title":"On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2404.02499","title":"Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2406.04935","title":"SLOPE: Search with Learned Optimal Pruning-based Expansion","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2605.03625","title":"Self-Improvement for Fast, High-Quality Plan Generation","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2207.05259","title":"Language-Based Causal Representation Learning","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2509.02794","title":"Learning General Policies From Examples","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2606.00618","title":"Efficient Test-time Inference for Generative Planning Models with OCL Search","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.10489","title":"A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}