In the context of reinforcement learning (RL), in order to increase trust in or understand the failings of an agent's policy, we propose predictive explanations in the form of three …
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most …
In recent years, reinforcement learning (RL) systems have shown impressive performance and remarkable achievements. Many achievements can be attributed to combining RL with …
For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often …
Y Septon, T Huber, E André, O Amir - … of Agents and Multi-Agent Systems, 2023 - Springer
Explainable reinforcement learning methods can roughly be divided into local explanations that analyze specific decisions of the agents and global explanations that convey the …
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains …
Z Yu, J Ruan, D Xing - arXiv preprint arXiv:2305.02749, 2023 - arxiv.org
Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for …
Generating counterfactuals to discover hypothetical predictive scenarios is the de facto standard for explaining machine learning models and their predictions. However, building a …
In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy …