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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied sciences Ročník 12; číslo 21; s. 10947
Hlavní autori: Terra, Ahmad, Inam, Rafia, Fersman, Elena
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Basel MDPI AG 01.11.2022
Predmet:
Artificial intelligence
Bias
Decomposition
deep reinforcement learning
explainability
explainable reinforcement learning
Methods
Neural networks
Performance evaluation
reward decomposition
reward prioritization
Variables
ISSN:2076-3417, 2076-3417
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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 analyze the contribution of the input side of the model, and reward decomposition methods are applied to explain the components of the output end of the RL model. In this study, we present a novel method to connect explanations from both input and output ends of a black-box model, which results in fine-grained explanations. Our method exposes the reward prioritization to the user, which in turn generates two different levels of explanation and allows RL agent reconfigurations when unwanted behaviors are observed. The method further summarizes the detailed explanations into a focus value that takes into account all reward components and quantifies the fulfillment of the explanation of desired properties. We evaluated our method by applying it to a remote electrical telecom-antenna-tilt use case and two openAI gym environments: lunar lander and cartpole. The results demonstrated fine-grained explanations by detailing input features’ contributions to certain rewards and revealed biases of the reward components, which are then addressed by adjusting the reward’s weights.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2076-3417
2076-3417
DOI:10.3390/app122110947