Search Results for author: Yiran Mao

Found 3 papers, 1 papers with code

Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity

no code implementations • 29 May 2023 • Yiran Mao, Madeline G. Reinecke, Markus Kunesch, Edgar A. Duéñez-Guzmán, Ramona Comanescu, Julia Haas, Joel Z. Leibo

Is it possible to evaluate the moral cognition of complex artificial agents?

Meta Reinforcement Learning reinforcement-learning

Paper
Add Code

Melting Pot 2.0

2 code implementations • 24 Nov 2022 • John P. Agapiou, Alexander Sasha Vezhnevets, Edgar A. Duéñez-Guzmán, Jayd Matyas, Yiran Mao, Peter Sunehag, Raphael Köster, Udari Madhushani, Kavya Kopparapu, Ramona Comanescu, DJ Strouse, Michael B. Johanson, Sukhdeep Singh, Julia Haas, Igor Mordatch, Dean Mobbs, Joel Z. Leibo

Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios.

Artificial Life Navigate

540

Paper
Code

Statistical discrimination in learning agents

no code implementations • 21 Oct 2021 • Edgar A. Duéñez-Guzmán, Kevin R. McKee, Yiran Mao, Ben Coppin, Silvia Chiappa, Alexander Sasha Vezhnevets, Michiel A. Bakker, Yoram Bachrach, Suzanne Sadedin, William Isaac, Karl Tuyls, Joel Z. Leibo

Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics.

Decision Making Multi-agent Reinforcement Learning

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.