paper-with-me

홈 › Papers

Subgoal Search For Complex Reasoning Tasks

2021-08-25 · NeurIPS 2021 12 · Konrad Czechowski, Tomasz Odrzygóźdź, Marek Zbysiński, Michał Zawalski, Krzysztof Olejnik, Yuhuai Wu, Łukasz Kuciński, Piotr Miłoś

Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. Using subgoals reduces the search space and induces a high-level search graph suitable for efficient planning. In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework. We show that a simple approach of generating $k$-th step ahead subgoals is surprisingly efficient on three challenging domains: two popular puzzle games, Sokoban and the Rubik's Cube, and an inequality proving benchmark INT. kSubS achieves strong results including state-of-the-art on INT within a modest computational budget.

📄 PDF Abstract BibTeX arXiv:2108.11204

Code (1)

subgoal-search/subgoal-search 공식 구현 pytorch

Tasks

DiversityRubik's CubeSokoban

Similar Papers 제목 키워드 기반

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

2022-06-01 · Michał Zawalski, Michał Tyrolski, Konrad Czechowski, Tomasz Odrzygóźdź 외

Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method tha…

Rubik's CubeSokoban

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

2024-10-18 · Jiacheng Ye, Jiahui Gao, Shansan Gong, Lin Zheng 외

Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a novel solution to these challenges. Through…

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?

2024-06-05 · Michał Zawalski, Gracjan Góral, Michał Tyrolski, Emilia Wiśnios 외

Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enhance planning by incorporating hierarchic…

Goal-Conditioned Reinforcement Learning with Imagined Subgoals

2021-07-01 · Elliot Chane-Sane, Cordelia Schmid, Ivan Laptev

Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it often struggles to solve tasks that require more temporally extended reasoning. In this work, we propose to incorporate imagi…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts

2024-01-01 · CVPR 2024 1 · Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou 외

Robotics agents often struggle to understand and follow the multi-modal prompts in complex manipulation scenes which are challenging to be sufficiently and accurately described by text alone. Moreover for long-horizo…

Image GenerationInstruction FollowingRobot ManipulationVisual Reasoning