Fig. 4

The average oracle score of the generated molecules increases at each round of adapting the MPO. At each round, a new batch of molecules is generated using an adapted scoring function after in total 110 queries (round 1) and 220 queries (round 2) to a simulated chemist. For comparison, we show round 0 that is the performance with the initial guess \({\theta }_{0}\). The bars show the mean of the average oracle score of the generated molecules over 10 random seeds, and the error bars represent one SEM. The gray horizontal line shows the average oracle score in 5000 molecules sampled from REINVENT without MPO objective, using its prior agent