BEERL: Both Ends Explanations for Reinforcement Learning

BEERL: Both Ends Explanations for Reinforcement Learning

Deep Reinforcement Learning (RL) is a black-box method and is hard to understand because the agent employs a neural network (NN). To explain the behavior and decisions made by the agent, different eXplainable RL (XRL) methods are developed; for example, feature importance methods are applied to anal...

Full description

Bibliographic Details
Main Authors: Ahmad Terra, Rafia Inam, Elena Fersman
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Applied Sciences
Subjects:
explainability
deep reinforcement learning
explainable reinforcement learning
reward decomposition
reward prioritization
bias
Online Access:https://www.mdpi.com/2076-3417/12/21/10947

Internet

https://www.mdpi.com/2076-3417/12/21/10947

Similar Items