# Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2111.02936 · HTML: https://mlsanity.com/paper/2111.02936/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates](https://mlsanity.com/paper/1610.00633/) (2016)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [Generating Counterfactual and Contrastive Explanations using SHAP](https://mlsanity.com/paper/1906.09293/) (2019)
- [Robotic Lever Manipulation using Hindsight Experience Replay and Shapley Additive Explanations](https://mlsanity.com/paper/2110.03292/) (2021)

## Built on by (most cited first, 4 of 4)

- [Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2306.05810/) (2023)
- [Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models](https://mlsanity.com/paper/2305.15167/) (2023)
- [Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications](https://mlsanity.com/paper/2207.01911/) (2022)
- [Approximating Shapley Explanations in Reinforcement Learning](https://mlsanity.com/paper/2511.06094/) (2025)

## Abstract (arXiv)

We investigate the effect of including domain knowledge about a robotic system's causal relations when generating explanations. To this end, we compare two methods from explainable artificial intelligence, the popular KernelSHAP and the recent causal SHAP, on a deep neural network trained using deep reinforcement learning on the task of controlling a lever using a robotic manipulator. A primary disadvantage of KernelSHAP is that its explanations represent only the features' direct effects on a model's output, not considering the indirect effects a feature can have on the output by affecting other features. Causal SHAP uses a partial causal ordering to alter KernelSHAP's sampling procedure to incorporate these indirect effects. This partial causal ordering defines the causal relations between the features, and we specify this using domain knowledge about the lever control task. We show that enabling an explanation method to account for indirect effects and incorporating some domain knowledge can lead to explanations that better agree with human intuition. This is especially favorable for a real-world robotics task, where there is considerable causality at play, and in addition, the required domain knowledge is often handily available.