Summary of An Empirical Investigation Of Value-based Multi-objective Reinforcement Learning For Stochastic Environments, by Kewen Ding et al.
An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments
by Kewen Ding, Peter Vamplew, Cameron Foale, Richard Dazeley
First submitted to arxiv on: 6 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 This research paper proposes a novel approach to solve Multi-Objective Reinforcement Learning (MORL) problems by extending conventional Q-learning using vector Q-values and utility functions. The study focuses on identifying factors influencing the frequency with which value-based MORL Q-learning algorithms learn the Scalarised Expected Reward (SER)-optimal policy in stochastic environments. Experiments with various algorithm variations and reward engineering approaches reveal limitations of these methods, highlighting the critical impact of noisy Q-value estimates on algorithm stability and convergence. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this research helps solve a complex problem in artificial intelligence called Multi-Objective Reinforcement Learning (MORL). The study looks at how to improve MORL algorithms that work well most of the time but struggle with certain types of environments. By testing different approaches and methods, researchers hope to create better MORL algorithms that can learn from experience and make good decisions even in tricky situations. |
Keywords
* Artificial intelligence * Reinforcement learning
