7520fa31d14f45add6d61e52df5a03ff-AuthorFeedback.pdf

Please see our responses below (Rn refers to Reviewer n). Lazaridou et al. 2020 also consider pragmatics during training, they do not use two-sided adjustment for each specific Details: Object candidate set C is for a single instance. In this case, the agents randomly select their actions. Compositionality is an important metric and we may add the following to Sec. 4.4: Topological We will amend our paper to better explain the experiments. Actually, we used this setting in the experiment, but it does not outperform IBR.