Reasoning in complex environments with the SelectScript declarative language
SelectScript is an extendable, adaptable, and declarative domain-specific language aimed at information retrieval from simulation environments and robotic world models in an SQL-like manner. In this work we have extended the language in two directions. First, we have implemented hierarchical queries; second, we improve efficiency enabling manual design space exploration on different "search" strategies. We demonstrate the applicability of such extensions in two application problems; the basic language concepts are explained by solving the classical problem of the Towers of Hanoi and then a common path planning problem in a complex 3D environment is implemented.
Code (3)
Tasks
Information RetrievalRetrievalSimilar Papers 제목 키워드 기반
Talking about the Moving Image: A Declarative Model for Image Schema Based Embodied Perception Grounding and Language Generation
We present a general theory and corresponding declarative model for the embodied grounding and natural language based analytical summarisation of dynamic visuo-spatial imagery. The declarative model ---ecompassing spatio…
Spatial ReasoningText GenerationThink in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Large language models (LLMs) excel at complex reasoning tasks such as mathematics and coding, yet they frequently struggle with simple interactive tasks that young children perform effortlessly. This discrepancy highligh…
Reinforcement LearningTowards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server Ecosystems
Recent advances in Large Language Models (LLMs) have enabled the development of increasingly complex agentic and multi-agent systems capable of planning, tool use and task decomposition. However, empirical evidence shows…
Robot Representation and Reasoning with Knowledge from Reinforcement Learning
Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Solving Math Word Problems by Combining Language Models With Symbolic Solvers
Automatically generating high-quality step-by-step solutions to math word problems has many applications in education. Recently, combining large language models (LLMs) with external tools to perform complex reasoning and…
GSM8KLanguage ModelingLanguage ModellingMath