What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
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 hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. In this study, we conduct an in-depth exploration of subgoal-planning methods for combinatorial reasoning. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts. We propose a consistent evaluation methodology to achieve meaningful comparisons between methods and reevaluate the state-of-the-art algorithms.
Code (1)
Similar Papers 제목 키워드 기반
Self-supervised Hierarchical Visual Reasoning with World Model
3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing …
Reinforcement LearningVisual ReasoningA Fuzzy Approach to Project Success: Measuring What Matters
This paper introduces a novel approach to project success evaluation by integrating fuzzy logic into an existing construct. Traditional Likert-scale measures often overlook the context-dependent and multifaceted nature o…
What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents
Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM planners to decompose tasks into language subgoals executed by low-level V…
Robot ManipulationQuantum Combinatorial Games: Structures and Computational Complexity
Recently, a standardized framework was proposed for introducing quantum-inspired moves in mathematical games with perfect information and no chance. The beauty of quantum games-succinct in representation, rich in structu…
Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is less often observed in long-horizon, contin…
Deep Reinforcement Learning