Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer
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.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement Learning (RL)SokobanSimilar Papers 제목 키워드 기반
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture
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)SokobanGraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies
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
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 ReasoningTowards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework
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
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