Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning
Learning a well-informed heuristic function for hard task planning domains is an elusive problem. Although there are known neural network architectures to represent such heuristic knowledge, it is not obvious what concrete information is learned and whether techniques aimed at understanding the structure help in improving the quality of the heuristics. This paper presents a network model to learn a heuristic capable of relating distant parts of the state space via optimal plan imitation using the attention mechanism, which drastically improves the learning of a good heuristic function. To counter the limitation of the method in the creation of problems of increasing difficulty, we demonstrate the use of curriculum learning, where newly solved problem instances are added to the training set, which, in turn, helps to solve problems of higher complexities and far exceeds the performances of all existing baselines including classical planning heuristics. We demonstrate its effectiveness for grid-type PDDL domains.
Code (0)
등록된 구현이 없습니다.
Tasks
Heuristic SearchTask PlanningSimilar Papers 제목 키워드 기반
Graph Value Iteration
In recent years, deep Reinforcement Learning (RL) has been successful in various combinatorial search domains, such as two-player games and scientific discovery. However, directly applying deep RL in planning domains is …
Deep Reinforcement LearningReinforcement Learning (RL)scientific discoveryGradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning
We demonstrate that gradient-based data valuation produces curriculum orderings that significantly outperform metadata-based heuristics for training game-theoretic motion planners. Specifically, we apply TracIn gradient-…
Motion PlanningEfficient Black-Box Planning Using Macro-Actions with Focused Effects
The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heurist…
Self-Evolving Curriculum for LLM Reasoning
Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influe…
Code GenerationPolicy Gradient MethodsReinforcement Learning (RL)Multi-Dimensional AGV Path Planning in 3D Warehouses Using Ant Colony Optimization and Advanced Neural Networks
Within modern warehouse scenarios, the rapid expansion of e-commerce and increasingly complex, multi-level storage environments have exposed the limitations of traditional AGV (Automated Guided Vehicle) path planning met…