- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes the Factorized Hanabi Agent (FHA), whose observation and action spaces are factorized by teammate, making the model independent of the number of players. A single FHA model can therefore be jointly trained across 2–5-player games and transferred zero-shot to unseen player counts.
Critical strengths
- Joint training across player counts reduces overfitting to setting-specific conventions and improves coordination with independently trained partners.
- The paper evaluates self-play, cross-play, and zero-shot transfer, and compares FHA with UPDeT, Other-Play, and Off-Belief Learning.
Critical weaknesses
- Entity-wise factorization and permutation-aware architectures have already been extensively studied. The proposed architecture does not appear to introduce a fundamentally new mechanism and is evaluated only on Hanabi, limiting the broader significance of the contribution. Moreover, combining FHA with Off-Belief Learning appears somewhat modular or incremental, without a sufficiently clear motivation or a strong claim regarding their compatibility.
- The core methodological design closely resembles techniques established in previous literature, particularly entity-wise decomposition, parameter sharing, and permutation-equivariant processing. The paper does not clearly distinguish its method from prior work or demonstrate a substantial conceptual advance beyond adapting these ideas to Hanabi.
- The results in Figures 2 and 3 do not show consistent or meaningful improvements over the baselines. In several settings, FHA appears comparable to—or weaker than—existing methods.
Questions for authors
Please refer to weakness.
Thank you for your feedback, comments and review. We have addressed common questions such as the failure modes of OBL and the inter-algorithmic cross-play in a general comment, and focus on specific comments here.
We agree that we do not introduce fundamentally new mechanisms, and our methodological approach takes inspiration from many of the existing works in the literature. However, we want to emphasize that proposing a new factorized architecture is not the main focus of our work. The main message we want to convey is that, under certain circumstances, one can use simple self-play training and still perform ad-hoc cooperation with unseen partners. This observation is of interest to the community because 1) ad-hoc cooperation is a fundamental desired property of multi-agent learning, 2) self-play is one of the simplest multi-agent learning algorithms there is. Simply by training on multiple settings jointly, one can use a very simple algorithm to achieve a crucial property for cooperative learning.
In contrast, many of the works on entity-wise decomposition (Wang et al., 2020; Iqbal et al., 2021), parameter sharing (De Witt et al., 2020), and permutation-equivariant processing (Hao et al., 2023; Park et al., 2025) focus on learning efficiency and team performance. UPDeT (Hu et al., 2021b) performs transfer experiments on variable player count, but keeps self-play as an evaluation procedure.
Thus, in our work, factorization is but a means to achieve multi-setting training, unlocking ad-hoc cooperation in the process.
IQL-LSTM does not show any cross-play performance, which is to be expected. Moreover, while FHA trained in a single setting shows some cross-play performance thanks to a restricted factorized observation-space, it is not on par with FHA trained in multi-player settings. This shows the effect training on multiple player-settings has on self-play agents. We agree that UPDeT also displays good cross-play performance, but this does not contradict our results: UPDeT was trained in self-play, on 2-5P games simultaneously as well. One main disadvantage of UPDeT lies in its training speed. Compared to FHA, it is 8-to-13 times slower in walltime (see Appendix A). Thus, our conclusion remains the same, and is showcased by 2 different network architectures.
Once again, thank you for your comments, they have helped us clarify and improve our work. We hope to have properly addressed your concerns, and would be glad to further discuss and clarify our work otherwise.