Update.

[picoclvr.git] / tasks.py

diff --git a/tasks.py b/tasks.py
index d680951..8b22cad 100755 (executable)
--- a/tasks.py
+++ b/tasks.py
@@ -1861,3 +1861,61 @@ class QMLP(Task):
 
 
 ######################################################################
+
+import escape
+
+
+class Escape(Task):
+    def __init__(
+        self,
+        nb_train_samples,
+        nb_test_samples,
+        batch_size,
+        height,
+        width,
+        T,
+        logger=None,
+        device=torch.device("cpu"),
+    ):
+        super().__init__()
+
+        self.batch_size = batch_size
+        self.device = device
+
+        states, actions, rewards = escape.generate_episodes(
+            nb_train_samples + nb_test_samples, height, width, T
+        )
+        seq = escape.episodes2seq(states, actions, rewards)
+        self.train_input = seq[:nb_train_samples]
+        self.test_input = seq[nb_train_samples:]
+
+        self.nb_codes = max(self.train_input.max(), self.test_input.max()) + 1
+
+        # if logger is not None:
+        # for s, a in zip(self.train_input[:100], self.train_ar_mask[:100]):
+        # logger(f"train_sequences {self.problem.seq2str(s)}")
+        # a = "".join(["01"[x.item()] for x in a])
+        # logger(f"                {a}")
+
+    def batches(self, split="train", nb_to_use=-1, desc=None):
+        assert split in {"train", "test"}
+        input = self.train_input if split == "train" else self.test_input
+        if nb_to_use > 0:
+            input = input[:nb_to_use]
+        if desc is None:
+            desc = f"epoch-{split}"
+        for batch in tqdm.tqdm(
+            input.split(self.batch_size), dynamic_ncols=True, desc=desc
+        ):
+            yield batch
+
+    def vocabulary_size(self):
+        return self.nb_codes
+
+    def produce_results(
+        self, n_epoch, model, result_dir, logger, deterministic_synthesis, nmax=1000
+    ):
+        pass
+
+
+######################################################################