Dataset
 

Explaining Reinforcement Learning To Mere Mortals: An Empirical Study - Supplementary Materials

Public Deposited
No preview available

Download the file

https://ir.library.oregonstate.edu/concern/datasets/tt44ps61c

Descriptions

Attribute NameValues
Creator
Abstract
  • "Explaining Reinforcement Learning to Mere Mortals: An Empirical Study This is the dataset for replicating our study, which was accepted to IJCAI '19. We present a user study to investigate the impact of explanations on non-experts’ understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanation type, reward-decomposition bars (predictions of future types of rewards). We designed a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in a simple Real-Time Strategy (RTS) game. Our results show that the combination of both saliency and reward bars were needed to achieve a statistically significant improvement in mental model score over the control. In addition, our qualitative analysis of the data reveals a number of effects for further study
License
Resource Type
DOI
Date Issued
Citation
  • Anderson, A. A. (2019). Explaining Reinforcement Learning To Mere Mortals: An Empirical Study - Supplementary Materials (Version 1) [Data set]. Oregon State University. https://doi.org/10.7267/tt44ps61c
Academic Affiliation
Subject
Rights Statement
Related Items
Funding Statement (additional comments about funding)
  • DARPA #N66001-17-2-4030
  • NSF #1314384
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

Items