2 Comments
User's avatar
Ditesh's avatar

Great adjacent read.

Open Problems in Cooperative AI

From Centre for the Governance of AI, Future of Humanity Institute, University of Oxford, DeepMind, University of Waterloo

https://arxiv.org/abs/2012.08630

Expand full comment
Ditesh's avatar

Casual Peer Review:

Conceptual leap – could be considered a spark of genius or at least high creativity.

Framework serves more as a philosophical guideline or a set of desired emergent properties for future MAS, rather than offering concrete algorithmic or architectural solutions

Provides interesting research questions and potential directions for MARL (e.g., exploring identity-based intrinsic motivation), but practical implementation requires significant breakthroughs in representation learning and reward design.

The framework serves as a rich source of phenomena for BGT/EGT researchers to target. It motivates the need for more sophisticated models incorporating dynamic identity and group-level agency but doesn't provide those models itself. It pushes the application boundaries of existing game theory.

It currently serves more as a thought-provoking extension than a developed technical proposal.

Expand full comment