DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 3 of its 9 references that are in the map. First posted on arXiv 5 Nov 2025.
Builds on
3 of 9 references.
References · 3
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2015Prioritized Experience Replaycited by 1,099
- 2020Revisiting Fundamentals of Experience Replaycited by 175
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025β-DQN: Improving Deep Q-Learning By Evolving the Behavior
- 2026A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer
- 2025GB-DQN: Gradient Boosted DQN Models for Non-stationary Reinforcement Learning
- 2025Universal Approximation Theorem of Deep Q-Networks
- 2025Value of Information-Enhanced Exploration in Bootstrapped DQN
- 2025Approximation to Deep Q-Network by Stochastic Delay Differential Equations
- 2024Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation
- 20252048: Reinforcement Learning in a Delayed Reward Environment