8
IRUS TotalDownloads
Altmetric
A causal perspective on AI deception in games
| File | Description | Size | Format | |
|---|---|---|---|---|
 paper2CAUSAL.pdf | Published version | 1.43 MB | Adobe PDF | View/Open |
| Title: | A causal perspective on AI deception in games |
| Authors: | Ward, F Toni, F Belardinelli, F |
| Item Type: | Conference Paper |
| Abstract: | Deception is a core challenge for AI safety and we focus on the problem that AI agents might learn deceptive strategies in pursuit of their objectives. We define the incentives one agent has to signal to and deceive another agent. We present several examples of deceptive artificial agents and show that our definition has desirable properties. |
| Issue Date: | 31-Jul-2022 |
| Date of Acceptance: | 3-Jun-2022 |
| URI: | http://hdl.handle.net/10044/1/104464 |
| Publisher: | CEUR Workshop Proceedings |
| Start Page: | 1 |
| End Page: | 16 |
| Journal / Book Title: | CEUR-ART |
| Copyright Statement: | © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). |
| Conference Name: | AI Safety 2022 (IJCAI-ECAI-22) |
| Publication Status: | Published |
| Start Date: | 2022-07-24 |
| Conference Place: | Vienna |
| Online Publication Date: | 2022-07-31 |
| Appears in Collections: | Computing |
This item is licensed under a Creative Commons License
