Summary of Provably Efficient Reinforcement Learning with Linear Function Approximation, by Chi Jin et al.
Provably Efficient Reinforcement Learning with Linear Function Approximation
by Chi Jin, Zhuoran Yang, Zhaoran Wang, Michael I. Jordan
First submitted to arxiv on: 11 Jul 2019
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC); Machine Learning (stat.ML)
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 tackles a fundamental challenge in Reinforcement Learning (RL) when dealing with large state spaces. Function approximation is often necessary to approximate the value function or policy, but this raises concerns about computational and statistical efficiency, particularly regarding exploration-exploitation trade-offs. The authors aim to design provably efficient RL algorithms that incorporate function approximation, even in simple settings like linear dynamics and rewards. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers are trying to solve a big problem in Reinforcement Learning. When there are many things the machine can do (states), they need to find ways to make good decisions without getting stuck in one place forever. This is hard because it’s hard to balance trying new things with sticking with what works. The goal is to create smart machines that can learn and make good choices. |
Keywords
* Artificial intelligence * Reinforcement learning
