paper-with-me

Papers

Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning

2020-06-04 · Dieqiao Feng, Carla P. Gomes, Bart Selman

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.

📄 PDF Abstract BibTeX arXiv:2006.02689

Code (1)

glassices/sokoban_planner pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Sokoban

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

2021-10-03 · NeurIPS 2020 12 · Dieqiao Feng, Carla P. Gomes, Bart Selman

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)Sokoban

Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks

2025-12-09 · Indrajit Kar, Kalathur Chenchu Kishore Kumar arxiv

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

2020-09-21 · Özgür Akgün, Nguyen Dang, Joan Espasa, Ian Miguel 외

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

2021-12-03 · Leah Chrestien, Tomas Pevny, Antonin Komenda, Stefan Edelkamp

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 Planning

Curriculum learning for multilevel budgeted combinatorial problems

2020-07-07 · NeurIPS 2020 12 · Adel Nabli, Margarida Carvalho

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