Summary of Multi-objective Deep Reinforcement Learning For Optimisation in Autonomous Systems, by Juan C. Rosero et al.
Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems
by Juan C. Rosero, Ivana Dusparic, Nicolás Cardozo
First submitted to arxiv on: 2 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 Reinforcement Learning (RL) is widely applied in Autonomous Systems (AS) as it allows learning at runtime without requiring an environment model or predefined actions. However, most RL applications in AS can only optimize one objective. To address this limitation, Multi-Objective Reinforcement Learning (MORL) techniques have been developed to combine multiple objectives with predefined weights. This paper explores the application of MORL’s Deep W-Learning (DWN) technique to Emergent Web Servers, a self-adaptive server, to optimize runtime performance. The authors compare DWN with two single-objective optimization approaches: epsilon-greedy algorithm and Deep Q-Networks. Initial evaluation shows that DWN successfully optimizes multiple objectives simultaneously, achieving similar results to the other methods, while avoiding issues associated with combining multiple objectives. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using a special kind of artificial intelligence called Reinforcement Learning (RL) in robots and self-driving cars. RL lets machines learn by trying different actions and seeing what happens. In this case, researchers are trying to use RL to make robots work better by finding the best way to combine multiple goals at once. They used a new technique called Deep W-Learning (DWN) and applied it to a special kind of robot that can adapt itself. The results show that DWN works well and is a good way to make decisions in complex situations. |
Keywords
» Artificial intelligence » Optimization » Reinforcement learning
