Summary of Learning to Play Video Games with Intuitive Physics Priors, by Abhishek Jaiswal and Nisheeth Srivastava
Learning to Play Video Games with Intuitive Physics Priors
by Abhishek Jaiswal, Nisheeth Srivastava
First submitted to arxiv on: 20 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
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 A novel approach to designing object-based input representations is proposed, which generalizes well across multiple video games. The method leverages simple inductive biases derived from intuitive representations of physics from the real world, allowing for effective Q-learning algorithm applications. The designed representation demonstrates superior generalizability, particularly for unfamiliar objects, outperforming prevailing methods that rely on image inputs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research explores a new way to help machines learn video games like humans do. Instead of using images as input, the approach focuses on object interactions and simple learning rules from everyday life. The result is an algorithm that can learn to play multiple games, even with objects it has never seen before. This human-like learning method shows promise for developing more intelligent AI. |
