有限环境中采用 Epsilon 贪心策略与优先经验回放的 DQN 性能研究
DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay
AI总结：
本文系统研究有限环境中 DQN 的 epsilon-greedy 探索调度与优先经验回放，通过多组仿真对比 uniform、no replay 和 prioritized 策略，揭示探索与记忆管理的权衡，并为资源受限场景提供强化学习实践建议。
摘要：
我们提出了对有限环境中 Deep Q-Networks 的详细研究，重点考察 epsilon-greedy 探索调度与 prioritized experience replay 的影响。通过系统实验，我们评估了 epsilon 衰减调度的变化如何影响学习效率、收敛行为和奖励优化。我们研究了 prioritized experience replay 如何带来更快的收敛和更高的回报，并展示了在多次仿真中比较 uniform、no replay 和 prioritized 策略的经验结果。我们的发现揭示了 DQN 训练中探索策略与记忆管理之间的权衡与交互，为资源受限环境下稳健的强化学习提供了实用建议。
英文摘要：
We present a detailed study of Deep Q-Networks in finite environments, emphasizing the impact of epsilon-greedy exploration schedules and prioritized experience replay. Through systematic experimentation, we evaluate how variations in epsilon decay schedules affect learning efficiency, convergence behavior, and reward optimization. We investigate how prioritized experience replay leads to faster convergence and higher returns and show empirical results comparing uniform, no replay, and prioritized strategies across multiple simulations. Our findings illuminate the trade-offs and interactions between exploration strategies and memory management in DQN training, offering practical recommendations for robust reinforcement learning in resource-constrained settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
