way to encode the underlying graph [R2] and a scalable approach to solving more complex domains [R3, R4] that

Thank you for the constructive feedback. We averaged the results over 10 random seeds. We will add more discussion on this to the future work section. Bi-LSTM runs considerably slower than the PPO and GCN baseline. In contrast, an RNN's output would depend on potentially all past states (in the case of LSTM/GRU this depends on the Because we essentially want to make predictions on the state space graph, local connectivity leads to better results.