# CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning

arXiv: https://arxiv.org/abs/2502.11896 · HTML: https://mlsanity.com/paper/2502.11896/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking](https://mlsanity.com/paper/2205.06750/) (2022)
- [Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking](https://mlsanity.com/paper/2406.03704/) (2024)

## Built on by (most cited first, 2 of 2)

- [DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents](https://mlsanity.com/paper/2506.12104/) (2025)
- [Agent2: An Agent-Generates-Agent Framework for Reinforcement Learning Automation](https://mlsanity.com/paper/2509.13368/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) in continuous action spaces encounters persistent challenges, such as inefficient exploration and convergence to suboptimal solutions. To address these limitations, we propose CAMEL, a novel framework integrating LLM-generated suboptimal policies into the RL training pipeline. CAMEL leverages dynamic action masking and an adaptive epsilon-masking mechanism to guide exploration during early training stages while gradually enabling agents to optimize policies independently. At the core of CAMEL lies the integration of Python-executable suboptimal policies generated by LLMs based on environment descriptions and task objectives. Although simplistic and hard-coded, these policies offer valuable initial guidance for RL agents. To effectively utilize these priors, CAMEL employs masking-aware optimization to dynamically constrain the action space based on LLM outputs. Additionally, epsilon-masking gradually reduces reliance on LLM-generated guidance, enabling agents to transition from constrained exploration to autonomous policy refinement. Experimental validation on Gymnasium MuJoCo environments demonstrates the effectiveness of CAMEL. In Hopper-v4 and Ant-v4, LLM-generated policies significantly improve sample efficiency, achieving performance comparable to or surpassing expert masking baselines. For Walker2d-v4, where LLMs struggle to accurately model bipedal gait dynamics, CAMEL maintains robust RL performance without notable degradation, highlighting the framework's adaptability across diverse tasks. While CAMEL shows promise in enhancing sample efficiency and mitigating convergence challenges, these issues remain open for further research. Future work aims to generalize CAMEL to multimodal LLMs for broader observation-action spaces and automate policy evaluation, reducing human intervention and enhancing scalability in RL training pipelines.