用大模型设计训练路径，让智能体更快学会玩二十一点。
Learning to Play Blackjack: A Curriculum Learning Perspective
- 用大模型动态生成分阶段训练任务，逐步引入复杂动作。
- 深度强化学习代理胜率提升至47.41%，爆牌率降至28.0%。
- 训练速度加快74%，适合想高效训练强化学习模型的研究者。
强化学习智能体在复杂环境中常面临效率与性能瓶颈。本文提出一种新框架，利用大语言模型（LLM）动态生成可执行动作的训练课程，使智能体能逐个学习动作。将该框架应用于八副牌真实模拟的二十一点游戏，为基于表格式Q-learning和深度Q网络（DQN）的智能体构建多阶段训练路径。在10次独立运行的评估中，基于课程的方法显著优于标准训练：DQN代理平均胜率从43.97%提升至47.41%，平均爆牌率由32.9%降至28.0%，整体训练流程提速超过74%，其完整训练耗时甚至短于基线方法的评估阶段。结果验证了大模型引导的课程设计能有效提升强化学习智能体的性能、鲁棒性与训练效率。
原文摘要 · Abstract (English)
Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the agent to incorporate each action individually. We apply this framework to the game of Blackjack, where the LLM creates a multi-stage training path that progressively introduces complex actions to a Tabular Q-Learning and a Deep Q-Network (DQN) agent. Our evaluation in a realistic 8-deck simulation over 10 independent runs demonstrates significant performance gains over standard training methods. The curriculum-based approach increases the DQN agent's average win rate from 43.97% to 47.41%, reduces the average bust rate from 32.9% to 28.0%, and accelerates the overall workflow by over 74%, with the agent's full training completing faster than the baseline's evaluation phase alone. These results validate that LLM-guided curricula can build more effective, robust, and efficient RL agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。