Relevance Score: A Landmark-Like Heuristic for Planning
- URL: http://arxiv.org/abs/2403.07510v1
- Date: Tue, 12 Mar 2024 10:45:45 GMT
- Title: Relevance Score: A Landmark-Like Heuristic for Planning
- Authors: Oliver Kim and Mohan Sridharan
- Abstract summary: We define a novel "relevance score" that helps identify facts or actions that appear in most but not all plans to achieve any given goal.
We experimentally compare the performance of our approach with that of a state of the art landmark-based planning approach using benchmark planning problems.
- Score: 9.912614726055129
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Landmarks are facts or actions that appear in all valid solutions of a
planning problem. They have been used successfully to calculate heuristics that
guide the search for a plan. We investigate an extension to this concept by
defining a novel "relevance score" that helps identify facts or actions that
appear in most but not all plans to achieve any given goal. We describe an
approach to compute this relevance score and use it as a heuristic in the
search for a plan. We experimentally compare the performance of our approach
with that of a state of the art landmark-based heuristic planning approach
using benchmark planning problems. While the original landmark-based heuristic
leads to better performance on problems with well-defined landmarks, our
approach substantially improves performance on problems that lack non-trivial
landmarks.
Related papers
- Exploring and Benchmarking the Planning Capabilities of Large Language Models [57.23454975238014]
We construct a benchmark suite encompassing both classical planning domains and natural language scenarios.
Second, we investigate the use of in-context learning (ICL) to enhance LLM planning, exploring the direct relationship between increased context length and improved planning performance.
Third, we demonstrate the positive impact of fine-tuning LLMs on optimal planning paths, as well as the effectiveness of incorporating model-driven search procedures.
arXiv Detail & Related papers (2024-06-18T22:57:06Z) - On the Markov Property of Neural Algorithmic Reasoning: Analyses and
Methods [94.72563337153268]
We present ForgetNet, which does not use historical embeddings and thus is consistent with the Markov nature of the tasks.
We also introduce G-ForgetNet, which uses a gating mechanism to allow for the selective integration of historical embeddings.
Our experiments, based on the CLRS-30 algorithmic reasoning benchmark, demonstrate that both ForgetNet and G-ForgetNet achieve better generalization capability than existing methods.
arXiv Detail & Related papers (2024-03-07T22:35:22Z) - Simple Hierarchical Planning with Diffusion [54.48129192534653]
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets.
We introduce the Hierarchical diffuser, a fast, yet surprisingly effective planning method combining the advantages of hierarchical and diffusion-based planning.
Our model adopts a "jumpy" planning strategy at the higher level, which allows it to have a larger receptive field but at a lower computational cost.
arXiv Detail & Related papers (2024-01-05T05:28:40Z) - Planning as In-Painting: A Diffusion-Based Embodied Task Planning
Framework for Environments under Uncertainty [56.30846158280031]
Task planning for embodied AI has been one of the most challenging problems.
We propose a task-agnostic method named 'planning as in-painting'
The proposed framework achieves promising performances in various embodied AI tasks.
arXiv Detail & Related papers (2023-12-02T10:07:17Z) - A Planning Ontology to Represent and Exploit Planning Knowledge for Performance Efficiency [6.87593454486392]
We consider the problem of automated planning, where the objective is to find a sequence of actions that will move an agent from an initial state of the world to a desired goal state.
We hypothesize that given a large number of available planners and diverse planning domains; they carry essential information that can be leveraged to identify suitable planners and improve their performance for a domain.
arXiv Detail & Related papers (2023-07-25T14:51:07Z) - Planning Landmark Based Goal Recognition Revisited: Does Using Initial
State Landmarks Make Sense? [9.107782510356989]
In this paper, we show that it does not provide any benefit to use landmarks that are part of the initial state in a planning landmark based goal recognition approach.
The empirical results show that omitting initial state landmarks for goal recognition improves goal recognition performance.
arXiv Detail & Related papers (2023-06-27T10:20:28Z) - Leveraging Planning Landmarks for Hybrid Online Goal Recognition [7.690707525070737]
We propose a hybrid method for online goal recognition that combines a symbolic planning landmark based approach and a data-driven goal recognition approach.
The proposed method is significantly more efficient in terms of computation time than the state-of-the-art but also improves goal recognition performance.
arXiv Detail & Related papers (2023-01-25T13:21:30Z) - PlanT: Explainable Planning Transformers via Object-Level
Representations [64.93938686101309]
PlanT is a novel approach for planning in the context of self-driving.
PlanT is based on imitation learning with a compact object-level input representation.
Our results indicate that PlanT can focus on the most relevant object in the scene, even when this object is geometrically distant.
arXiv Detail & Related papers (2022-10-25T17:59:46Z) - Learning off-road maneuver plans for autonomous vehicles [0.0]
This thesis explores the benefits machine learning algorithms can bring to online planning and scheduling for autonomous vehicles in off-road situations.
We present a range of learning-baseds to assist different itinerary planners.
In order to synthesize strategies to execute synchronized maneuvers, we propose a novel type of scheduling controllability and a learning-assisted algorithm.
arXiv Detail & Related papers (2021-08-02T16:27:59Z) - Long-Horizon Visual Planning with Goal-Conditioned Hierarchical
Predictors [124.30562402952319]
The ability to predict and plan into the future is fundamental for agents acting in the world.
Current learning approaches for visual prediction and planning fail on long-horizon tasks.
We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
arXiv Detail & Related papers (2020-06-23T17:58:56Z) - The More the Merrier?! Evaluating the Effect of Landmark Extraction
Algorithms on Landmark-Based Goal Recognition [25.6019435583572]
Recent approaches to goal and plan recognition using classical planning domains have achieved state of the art results in terms of both recognition time and accuracy.
To achieve such fast recognition time these approaches use efficient, but incomplete, algorithms to extract only a subset of landmarks for planning domains and problems.
In this paper, we investigate the impact and effect of using various landmark extraction algorithms capable of extracting a larger proportion of the landmarks for each given planning problem.
arXiv Detail & Related papers (2020-05-06T17:41:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.