Counterfactual States for Atari Agents via Generative Deep Learning
arXiv:1909.12969
Abstract
Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is a counterfactual, which deals with "what if?" scenarios. In this work, we introduce the concept of a counterfactual state to help humans gain a better understanding of what would need to change (minimally) in an Atari game image for the agent to choose a different action. We introduce a novel method to create counterfactual states from a generative deep learning architecture. In addition, we evaluate the effectiveness of counterfactual states on human participants who are not machine learning experts. Our user study results suggest that our generated counterfactual states are useful in helping non-expert participants gain a better understanding of an agent's decision making process.
IJCAI XAI Workshop 2019
References in corpus (6)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Visualizing and Understanding Atari Agents
- Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
- Programmatically Interpretable Reinforcement Learning
- Graying the black box: Understanding DQNs
- Learn to Interpret Atari Agents
Cited by in corpus (6)
- What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
- GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
- Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
- Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning
- Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
- Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations