Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning
Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit. In contrast to prior efforts, which use carefully handcrafted pruning techniques, our approach automatically uncovers domain structure. Our results reveal that deep RL provides a promising framework for solving previously unsolved AI planning problems, provided a proper training curriculum can be devised.
Code (1)
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)SokobanMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
In recent years, we have witnessed tremendous progress in deep reinforcement learning (RL) for tasks such as Go, Chess, video games, and robot control. Nevertheless, other combinatorial domains, such as AI planning, stil…
Deep Reinforcement LearningReinforcement Learning (RL)SokobanCurriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks
Large Language Models and multi-agent systems have shown promise in decomposing complex tasks, yet they struggle with long-horizon reasoning tasks and escalating computation cost. This work introduces a hierarchical mult…
Exploring Instance Generation for Automated Planning
Many of the core disciplines of artificial intelligence have sets of standard benchmark problems well known and widely used by the community when developing new algorithms. Constraint programming and automated planning a…
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 concre…
Heuristic SearchTask PlanningCurriculum learning for multilevel budgeted combinatorial problems
Learning heuristics for combinatorial optimization problems through graph neural networks have recently shown promising results on some classic NP-hard problems. These are single-level optimization problems with only one…
Combinatorial OptimizationMulti-agent Reinforcement Learning