dtControl2+$\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees
Over the past decade, decision trees have been used to represent controllers (a.k.a. policies) in an explainable way, with dtControl2 as a current state-of-the-art tool. However, for systems that are large or have many corner cases, even such representations tend to be too complex and not human-comprehensible. Unfortunately, reducing the size of the decision tree is not straightforward, as missing just a single crucial case might result in an incorrect controller. We tackle this issue in the setting of Markov decision processes, extending dtControl2 by "$\varepsilon$" functionality: Given an allowed imprecision $\varepsilon \geq 0$, we construct a smaller decision tree, distilling the essence of the controller, while still guaranteeing its $\varepsilon$-optimality. This enables us to provi
通过决策树优化MDP控制器的可解释性与简洁性。
- 核心方法
- 基于 dtControl2 工具，引入了“ε”功能，即允许一定的非最优性（imprecision），以牺牲轻微的性能为代价构建更小、更易于理解的决策树。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 在大规模或拥有多个特殊情况的系统中，传统的决策树表示的控制器难以保持简洁且可理解，同时确保正确性。
- 关键实验
- 对多个标准MDP问题进行了实验，展示了新方法在简化决策树的同时保持了控制器性能。
- 主要贡献
- 提出了一种在保持控制器 ε-最优性的同时，显著减少决策树大小和复杂度的方法。
- 意义与局限
- 该方法提高了MDP控制器的可解释性，使得决策过程更容易被人类理解，但可能在极少数情况下牺牲一些最优性。