基于强化学习行为模型(RLBM)的教学探索——以Python语言程序设计为例
Teaching Exploration Based on the Reinforcement Learning Behavior Model (RLBM)—Taking Python Language Programming as an Example

随着信息技术的飞速发展，Python语言的学习愈发关键，但其传统教学模式在培育学生实践能力上渐显乏力。本研究通过剖析传统教学的弊端，梳理国内外关于Python语言教学改革的成果，提出了基于强化学习行为模型(RLBM)行为模式的教学改革思路。RLBM由：智能体(agent)、环境(environment)、动作(action)和奖励(reward)四大核心要素构成，学生通过不断试错，依据环境反馈的奖励信号来学习最优策略。该教学方法在四川大学锦江学院进行了教学实践，结果表明，此方法极大提升了教学成效、并有效激发了学生自主学习能力，为程序设计类课程教学改革提供创新性的思路与实践参考。
With the rapid development of information technology, learning the Python language has become increasingly crucial. However, the traditional teaching model is gradually showing its inadequacy in cultivating students’ practical abilities. This research analyzes the drawbacks of traditional teaching, sorts out the achievements of Python language teaching reform both at home and abroad, and puts forward the ideas for teaching reform based on the behavior mode of the Reinforcement Learning Behavior Model (RLBM). The RLBM consists of five core elements: agent, environment, state, action, and reward. Students learn the optimal strategies by constantly making trial-and-error attempts and relying on the reward signals fed back by the environment. This teaching method has been implemented in teaching practice at Jinjiang College of Sichuan University. The results show that this method has significantly improved teaching effectiveness and effectively stimulated students’ autonomous learning ability, providing innovative ideas and practical references for the teaching reform of programming courses.