# Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs

arXiv: https://arxiv.org/abs/2202.04943 · HTML: https://mlsanity.com/paper/2202.04943/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Challenges of Real-World Reinforcement Learning](https://mlsanity.com/paper/1904.12901/) (2019)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [Noisy Networks for Exploration](https://mlsanity.com/paper/1706.10295/) (2017)
- [First return, then explore](https://mlsanity.com/paper/2004.12919/) (2020)
- [Do Feature Attribution Methods Correctly Attribute Features?](https://mlsanity.com/paper/2104.14403/) (2021)
- [Online and Offline Reinforcement Learning by Planning with a Learned Model](https://mlsanity.com/paper/2104.06294/) (2021)
- [Model Interpretability through the Lens of Computational Complexity](https://mlsanity.com/paper/2010.12265/) (2020)
- [Neuroevolution of Self-Interpretable Agents](https://mlsanity.com/paper/2003.08165/) (2020)
- [Evolutionary learning of interpretable decision trees](https://mlsanity.com/paper/2012.07723/) (2020)
- [Learning a Formula of Interpretability to Learn Interpretable Formulas](https://mlsanity.com/paper/2004.11170/) (2020)
- [Towards Interpretable-AI Policies Induction using Evolutionary Nonlinear Decision Trees for Discrete Action Systems](https://mlsanity.com/paper/2009.09521/) (2020)
- [GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning](https://mlsanity.com/paper/2106.06232/) (2021)

## Built on by (most cited first, 2 of 2)

- [Quality Diversity Evolutionary Learning of Decision Trees](https://mlsanity.com/paper/2208.12758/) (2022)
- [Interpretable AI for policy-making in pandemics](https://mlsanity.com/paper/2204.04256/) (2022)

## Abstract (arXiv)

The importance of explainability in AI has become a pressing concern, for which several explainable AI (XAI) approaches have been recently proposed. However, most of the available XAI techniques are post-hoc methods, which however may be only partially reliable, as they do not reflect exactly the state of the original models. Thus, a more direct way for achieving XAI is through interpretable (also called glass-box) models. These models have been shown to obtain comparable (and, in some cases, better) performance with respect to black-boxes models in various tasks such as classification and reinforcement learning. However, they struggle when working with raw data, especially when the input dimensionality increases and the raw inputs alone do not give valuable insights on the decision-making process. Here, we propose to use end-to-end pipelines composed of multiple interpretable models co-optimized by means of evolutionary algorithms, that allows us to decompose the decision-making process into two parts: computing high-level features from raw data, and reasoning on the extracted high-level features. We test our approach in reinforcement learning environments from the Atari benchmark, where we obtain comparable results (with respect to black-box approaches) in settings without stochastic frame-skipping, while performance degrades in frame-skipping settings.