NeurIPS 2020

Joint Policy Search for Multi-agent Collaboration with Imperfect Information


Meta Review

This paper presents the concept of policy density change for collaborative imperfect information games. All the reviewers agree that the idea is novel, appreciating the results in small games and in a much larger game of bridge (in particular, a comparison vs. WBridge5). There are several problems identified that the reviewers agree to be characterized as minor enough to be address in the final copy. As noted, there are problems with the comparison to WBridge5 and the authors have agreed to change their claim as a result. Clarifications on the connections to CFR and subgame decomposition should be made. Finally, several reviewers brought up that authors seem dismissive or reluctant to admit the weaknesses of their approach. This could affect the long-term impact of the paper. In particular, in the discussion the reviewers seem skeptical that the approach could be as easily extended to the general-sum case as implied in the author response, and stated that such speculation could actually be harmful to the paper's narrative. I strongly encourage the authors to consider this feedback when improving the paper