Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations
| Autor: | Melinda T. Gervasio, Pedro Sequeira |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Linguistics and Language Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence media_common.quotation_subject Computer Science - Human-Computer Interaction Machine Learning (stat.ML) 02 engineering and technology Language and Linguistics Task (project management) Machine Learning (cs.LG) Human-Computer Interaction (cs.HC) Artificial Intelligence (cs.AI) Artificial Intelligence Human–computer interaction Statistics - Machine Learning 020204 information systems 0202 electrical engineering electronic engineering information engineering Key (cryptography) Reinforcement learning 020201 artificial intelligence & image processing Aptitude Diversity (business) media_common |
| DOI: | 10.48550/arxiv.1912.09007 |
| Popis: | We propose an explainable reinforcement learning (XRL) framework that analyzes an agent's history of interaction with the environment to extract interestingness elements that help explain its behavior. The framework relies on data readily available from standard RL algorithms, augmented with data that can easily be collected by the agent while learning. We describe how to create visual summaries of an agent's behavior in the form of short video-clips highlighting key interaction moments, based on the proposed elements. We also report on a user study where we evaluated the ability of humans to correctly perceive the aptitude of agents with different characteristics, including their capabilities and limitations, given visual summaries automatically generated by our framework. The results show that the diversity of aspects captured by the different interestingness elements is crucial to help humans correctly understand an agent's strengths and limitations in performing a task, and determine when it might need adjustments to improve its performance. Comment: To appear in: Artificial Intelligence |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|