Accessing background returns for evaluation results

[s-a-barnett]

I am interested in looking at the collective rewards achieved by the exploiter MAPLA agents that were trained for the Melting Pot 2.0 report. In the evaluation_results.ipynb notebook, the results are downloaded from the path https://storage.googleapis.com/dm-meltingpot/meltingpot-results-2.1.1.feather, which contains the focal per capita returns for the exploiters, but not the background per capita returns for the agents they were trained against. Would it be possible to access the data so that I can make evaluations of the collective returns achieved in these scenarios?