paper-with-me

홈 › Papers

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer

2019-09-25 · Daniel Tanneberg, Elmar Rueckert, Jan Peters

A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems. Therefore, we present a novel architecture, based on memory-augmented networks, that is inspired by the von Neumann and Harvard architectures of modern computers. This architecture enables the learning of abstract algorithmic solutions via Evolution Strategies in a reinforcement learning setting. Applied to Sokoban, sliding block puzzle and robotic manipulation tasks, we show that the architecture can learn algorithmic solutions with strong generalization and abstraction: scaling to arbitrary task configurations and complexities, and being independent of both the data representation and the task domain.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)Sokoban

Similar Papers 제목 키워드 기반

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture

2019-10-30 · Daniel Tanneberg, Elmar Rueckert, Jan Peters

A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems. Therefore, we present a novel architecture, based on memory-augmented networks, that is inspired by …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Sokoban

GraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies

2025-11-06 · Maëlic Neau, Zoe Falomir, Paulo E. Santos, Anne-Gwenn Bosser 외 arxiv

Deploying autonomous robots that can learn new skills from demonstrations is an important challenge of modern robotics. Existing solutions often apply end-to-end imitation learning with Vision-Language Action (VLA) model…

Neural Sequence-to-grid Module for Learning Symbolic Rules

2021-01-13 · Segwang Kim, Hyoungwook Nam, Joonyoung Kim, Kyomin Jung

Logical reasoning tasks over symbols, such as learning arithmetic operations and computer program evaluations, have become challenges to deep learning. In particular, even state-of-the-art neural networks fail to achieve…

Logical Reasoning

Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework

2026-06-26 · Jiajing Zhang, Jiamei Jiang, Chenyang Zhang, Feifei Mo 외 arxiv

Large language models (LLMs) have attracted widespread attention from academia and industry, yet their deployment raises critical security concerns regarding robustness and reliability. Planning, a core component of inte…

LOOP: A Plug-and-Play Neuro-Symbolic Framework for Enhancing Planning in Autonomous Systems

2025-08-18 · Ronit Virwani, Ruchika Suryawanshi arxiv

Planning is one of the most critical tasks in autonomous systems, where even a small error can lead to major failures or million-dollar losses. Current state-of-the-art neural planning approaches struggle with complex do…

Natural Language Understanding