-To run the experiments:
+To train the shortest-path solving GPT, and train the one-shot MLP
+read-out:
- ./beaver.py
+ ./beaver.py --oneshot
-to train the shortest-path solving GPT, and
+Same, lighter settings (~95% test success instead of ~99%):
- ./beaver.py --overwrite --one_shot --nb_epochs=10
-
-to train the one-shot MLP read-out.
+ ./beaver.py --nb_train_samples=25000 --nb_test_samples=10000 --oneshot