A-LAMP: Agentic LLM-Based Framework for Automated MDP Modeling and Policy Generation

TL;DR

A-LAMP is a novel framework that automates the translation of natural language task descriptions into formal MDP models and policies using large language models, improving accuracy and reliability in reinforcement learning applications.

Contribution

It introduces an agentic LLM-based pipeline that automates MDP modeling and policy generation, ensuring semantic alignment and high performance across domains.

Findings

A-LAMP outperforms single state-of-the-art LLM models in policy generation.

Even lightweight variants of A-LAMP approach larger models' performance.

The framework maintains task optimality and semantic correctness.

Abstract

Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is challenging due to modeling errors, fragile code, and misaligned objectives, which often impede policy training. We introduce an agentic large language model (LLM)-based framework for automated MDP modeling and policy generation (A-LAMP), that automatically translates free-form natural language task descriptions into an MDP formulation and trained policy. The framework decomposes modeling, coding, and training into verifiable stages, ensuring semantic alignment throughout the pipeline. Across both classic control and custom RL domains, A-LAMP consistently achieves higher policy generation capability than a single state-of-the-art LLM model. Notably, even its lightweight variant, which is built on smaller language models, approaches the performance of much larger models. Failure analysis reveals why these improvements occur. In addition, a case study also demonstrates that A-LAMP generates environments and policies that preserve the task's optimality, confirming its correctness and reliability.