Summary of Exploiting Symmetry in Dynamics For Model-based Reinforcement Learning with Asymmetric Rewards, by Yasin Sonmez et al.
Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
by Yasin Sonmez, Neelay Junnarkar, Murat Arcak
First submitted to arxiv on: 27 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO); Systems and Control (eess.SY)
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 explores novel applications of symmetries in reinforcement learning, extending the scope of problems that can be tackled using symmetry techniques. It proposes a new approach to learn dynamics that exhibit specified symmetries, which is essential for improving sample efficiency in training policies. The method builds upon Cartan’s moving frame technique and is demonstrated through numerical experiments to accurately model dynamic systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps make reinforcement learning more efficient by using symmetry in the dynamics of a system, rather than relying on both dynamics and rewards having the same symmetry. This means we can apply symmetry techniques to a wider range of problems, including those that involve complex dynamic systems. The new method is tested and shown to accurately model these dynamic systems. |
Keywords
* Artificial intelligence * Reinforcement learning
