Summary of Learning Pareto Set For Multi-objective Continuous Robot Control, by Tianye Shu and Ke Shang and Cheng Gong and Yang Nan and Hisao Ishibuchi
Learning Pareto Set for Multi-Objective Continuous Robot Control
by Tianye Shu, Ke Shang, Cheng Gong, Yang Nan, Hisao Ishibuchi
First submitted to arxiv on: 27 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); 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 research proposes a simple and resource-efficient multi-objective reinforcement learning (MORL) algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. The proposed method is compared with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems, achieving the best overall performance with the least training parameters. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps us better understand how to solve complex control problems that involve multiple goals or objectives. Instead of finding a single “best” solution, we can learn many different solutions that all work well in their own way. The researchers propose a new algorithm that makes it easier and more efficient to find these different solutions, which is useful for controlling robots and other machines. |
Keywords
* Artificial intelligence * Reinforcement learning
