NeurIPS 2020

Incorporating Pragmatic Reasoning Communication into Emergent Language


Meta Review

All reviewers agree that this is an interesting, sound submission above acceptance threshold. I have read the reviews and author response and I would like to propose acceptance. Specifically, I agree with R1 that the idea of considering explicit equilibria methods in the context of multi-agent communication will inspire more research in the field. Moreover, the application on Starcraft domain is also a good contribution and overall this work provides good accuracy-based improvements with the proposed pragmatic reasoning method. However, I agree with R1 that a discussion beyond accuracy results (e.g., looking at the intrinsic properties of the learned communication) would have been really helpful. At the same time, the reviewers have raised a number of concerns, most of which appear have been clarified in the author response. In particular I think clarifying in the final manuscript the points raised by R1 and R2 (and the subsequent author responses) would improve the clarity of the paper.