调优探索与记忆策略，显著提升DQN在有限环境中的学习效率和收益。
DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay
- 对比不同epsilon衰减策略对学习效率的影响
- 优先经验回放使收敛更快、回报更高
- 适合资源受限场景下的强化学习实践
我们针对有限环境中的深度Q网络（DQN）进行了深入研究，重点分析epsilon-greedy探索策略和优先经验回放的影响。通过系统实验，评估了epsilon衰减策略变化对学习效率、收敛行为和奖励优化的影响。研究发现，优先经验回放可加快收敛速度并提升最终回报，并在多个模拟中对比了均匀回放、无回放与优先回放策略的性能。结果揭示了探索策略与记忆管理之间的权衡与交互关系，为资源受限环境下的强化学习提供了实用建议。
原文摘要 · Abstract (English)
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.
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。