Summary of Federated Learning Of Socially Appropriate Agent Behaviours in Simulated Home Environments, by Saksham Checker and Nikhil Churamani and Hatice Gunes
Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments
by Saksham Checker, Nikhil Churamani, Hatice Gunes
First submitted to arxiv on: 12 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Robotics (cs.RO)
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 presents two novel benchmarks for evaluating Federated Learning and Federated Continual Learning strategies in multi-agent settings. The first benchmark evaluates different methods for predicting the social appropriateness of robot actions using multi-label regression objectives. The second benchmark adapts these methods to use state-of-the-art continual learning techniques, allowing agents to learn incrementally across different contextual settings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how robots can work together and learn from each other’s experiences. It creates two new ways to test how well this happens. One way looks at how well individual robots can predict what actions are socially acceptable. The other way adds the challenge of learning in different situations, like morning or evening. The results show that a method called Federated Averaging is good at sharing knowledge between robots, and another method called rehearsal-based learning helps agents learn new skills over time. |
Keywords
* Artificial intelligence * Continual learning * Federated learning * Regression
