Summary of Stacked Universal Successor Feature Approximators For Safety in Reinforcement Learning, by Ian Cannon et al.
Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning
by Ian Cannon, Washington Garcia, Thomas Gresavage, Joseph Saurine, Ian Leong, Jared Culbertson
First submitted to arxiv on: 6 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 This paper proposes a novel approach to solving complex real-world problems that involve multiple objectives and constraints. The method, called Stacked Universal Successor Feature Approximation for Safety (SUSFAS), combines the universal successor feature approximation algorithm with soft actor-critic and secondary safety controllers. SUSFAS improves performance on secondary objectives compared to traditional SAC baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about solving real-world problems that have many goals and rules. Right now, we don’t have a good way to make machines learn how to do this. The authors are trying to fix this problem by combining two existing methods: soft actor-critic and universal successor feature approximation. They add some extra safety controllers to make sure the machine doesn’t get stuck or make things worse. This new method is better at achieving its secondary goals than what we have now. |
