-To run the experiments:
+To train the shortest-path solving GPT, and train the one-shot MLP
+read-out:
- ./beaver.py
-
-to train the shortest-path solving GPT, and
-
- ./beaver.py --overwrite --one_shot --nb_epochs=10
-
-to train the one-shot MLP read-out.
+ ./beaver.py --oneshot
parser.add_argument("--oneshot_input", type=str, default="head")
-parser.add_argument("--oneshot_output", type=str, default="policy")
+parser.add_argument("--oneshot_output", type=str, default="trace")
######################################################################