Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL

no code implementations • 4 Jun 2022 • Kin-Ho Lam, Delyar Tabatabai, Jed Irvine, Donald Bertucci, Anita Ruangrotsakun, Minsuk Kahng, Alan Fern

Reinforcement learning (RL) agents are commonly evaluated via their expected value over a distribution of test scenarios.

Reinforcement Learning (RL)

Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations

no code implementations • 28 Sep 2021 • Kin-Ho Lam, Zhengxian Lin, Jed Irvine, Jonathan Dodge, Zeyad T Shureih, Roli Khanna, Minsuk Kahng, Alan Fern

We describe a user interface and case study, where a small group of AI experts and developers attempt to identify reasoning flaws due to inaccurate agent learning.

Decision Making Reinforcement Learning (RL)

Explaining Reinforcement Learning to Mere Mortals: An Empirical Study

no code implementations • 22 Mar 2019 • Andrew Anderson, Jonathan Dodge, Amrita Sadarangani, Zoe Juozapaitis, Evan Newman, Jed Irvine, Souti Chattopadhyay, Alan Fern, Margaret Burnett

We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents.

reinforcement-learning Reinforcement Learning (RL)

Multi-Label Classifier Chains for Bird Sound

no code implementations • 22 Apr 2013 • Forrest Briggs, Xiaoli Z. Fern, Jed Irvine

Bird sound data collected with unattended microphones for automatic surveys, or mobile devices for citizen science, typically contain multiple simultaneously vocalizing birds of different species.

General Classification Multi-Label Classification +1