Summary of Double Successive Over-relaxation Q-learning with An Extension to Deep Reinforcement Learning, by Shreyas S R
Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning
by Shreyas S R
First submitted to arxiv on: 10 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a new Q-learning algorithm that addresses the limitations of existing methods by introducing a relaxation factor to speed up convergence. The algorithm, called double SOR Q-learning, is shown to be less biased than previous approaches and can be applied to large-scale problems using deep reinforcement learning. The proposed method is theoretically analyzed and empirically tested on various environments, including grid world, roulette, OpenAI Gym, and a maximization bias example. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper improves upon existing Q-learning algorithms by introducing a relaxation factor to speed up convergence. This new algorithm, called double SOR Q-learning, is shown to be less biased than previous approaches. The authors test their method on various environments, including simple games like grid world and roulette, as well as more complex problems using deep reinforcement learning. |
Keywords
» Artificial intelligence » Reinforcement learning
