paper-with-me

홈 › Papers

Classical Planning in Deep Latent Space

2021-06-30 · Masataro Asai, Hiroshi Kajino, Alex Fukunaga, Christian Muise

Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We evaluate Latplan using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.

📄 PDF Abstract BibTeX arXiv:2107.00110

Code (1)

guicho271828/latplan 공식 구현 tf

Tasks

Deep LearningSokoban

Similar Papers 제목 키워드 기반

Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary

2017-04-29 · Masataro Asai, Alex Fukunaga

Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved signific…

Plausibility-Based Heuristics for Latent Space Classical Planning

2023-06-20 · Yuta Takata, Alex Fukunaga

Recent work on LatPlan has shown that it is possible to learn models for domain-independent classical planners from unlabeled image data. Although PDDL models acquired by LatPlan can be solved using standard PDDL planner…

valid

Planning in Dynamic Environments with Conditional Autoregressive Models

2018-11-25 · Johanna Hansen, Kyle Kastner, Aaron Courville, Gregory Dudek

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, …

Hierarchical Planning with Latent World Models

2026-04-03 · Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis 외 arxiv

World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction errors compound and naive search is exponen…

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning

2022-12-08 · Onur Beker, Mohammad Mohammadi, Amir Zamir

To achieve autonomy in a priori unknown real-world scenarios, agents should be able to: i) act from high-dimensional sensory observations (e.g., images), ii) learn from past experience to adapt and improve, and iii) be c…

Q-LearningRepresentation Learning