Abstracted Trajectory Visualization for Explainability in Reinforcement Learning

February 05, 2024 Β· Declared Dead Β· πŸ› Conference on Algebraic Informatics

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yoshiki Takagi, Roderick Tabalba, Nurit Kirshenbaum, Jason Leigh arXiv ID 2402.07928 Category cs.HC: Human-Computer Interaction Cross-listed cs.AI, cs.LG Citations 1 Venue Conference on Algebraic Informatics Last Checked 4 months ago
Abstract
Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted