Summary of Information-theoretic State Variable Selection For Reinforcement Learning, by Charles Westphal et al.
Information-Theoretic State Variable Selection for Reinforcement Learning
by Charles Westphal, Stephen Hailes, Mirco Musolesi
First submitted to arxiv on: 21 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Theory (cs.IT)
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 This paper tackles a fundamental challenge in Reinforcement Learning (RL), namely identifying the most suitable variables to represent the state. The authors propose the Transfer Entropy Redundancy Criterion (TERC) to determine if there is entropy transferred from state variables to actions during training. Based on TERC, they develop an algorithm that excludes variables with no effect on the agent’s performance, leading to more sample-efficient learning. Experimental results demonstrate this speed-up across three RL algorithms and various environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps solve a big problem in Reinforcement Learning. Imagine you’re trying to teach a robot or computer program to make good decisions. To do that, you need to figure out which pieces of information are most important for making those decisions. The authors introduce a new way to find the right information by looking at how it’s connected to the actions the agent takes. This helps the agent learn faster and better. The paper shows that this method works well across different types of algorithms and real-world scenarios. |
Keywords
* Artificial intelligence * Reinforcement learning
