X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=problems.py;h=ac16df4060f58a929ded208acf239a7706681edf;hb=8d9cd6a2c09da2105ca17b04df94fcf84e8de954;hp=675a47ae5e86ebe3df318cb653a98503ba930eba;hpb=b108aef212afc9b37ece29bea44f35b8686aac02;p=picoclvr.git

diff --git a/problems.py b/problems.py
index 675a47a..ac16df4 100755
--- a/problems.py
+++ b/problems.py
@@ -24,6 +24,8 @@ class Problem:
 
 
 ####################
+
+
 class ProblemDegradation(Problem):
     def __init__(self, nb_state_tokens=5, nb_time_steps=12, value_max=25, hard=False):
         assert value_max // nb_state_tokens >= 2
@@ -287,30 +289,58 @@ class ProblemAddition(Problem):
 
 
 class ProblemMixing(Problem):
-    def __init__(self, height=3, width=3, nb_time_steps=12, hard=False):
+    def __init__(
+        self, height=4, width=4, nb_time_steps=9, hard=False, random_start=True
+    ):
         self.height = height
         self.width = width
         self.nb_time_steps = nb_time_steps
         self.hard = hard
+        self.random_start = random_start
 
     def start_random(self, nb):
         y = torch.arange(self.height * self.width).reshape(1, -1).expand(nb, -1)
 
-        m = (torch.rand(y.size()).sort(dim=-1).indices < y.size(1) // 2).long()
+        if self.random_start:
+            i = (
+                torch.arange(self.height)
+                .reshape(1, -1, 1)
+                .expand(nb, self.height, self.width)
+            )
+            j = (
+                torch.arange(self.width)
+                .reshape(1, 1, -1)
+                .expand(nb, self.height, self.width)
+            )
+
+            ri = torch.randint(self.height, (nb,)).reshape(nb, 1, 1)
+            rj = torch.randint(self.width, (nb,)).reshape(nb, 1, 1)
 
-        y = (y * m + self.height * self.width * (1 - m)).reshape(
-            nb, self.height, self.width
-        )
+            m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
+
+            y = y * m + self.height * self.width * (1 - m)
+
+        y = y.reshape(nb, self.height, self.width)
 
         return y
 
     def start_error(self, x):
+        i = torch.arange(self.height, device=x.device).reshape(1, -1, 1).expand_as(x)
+        j = torch.arange(self.width, device=x.device).reshape(1, 1, -1).expand_as(x)
+
+        ri = (
+            (x == self.height * self.width).long().sum(dim=-1).argmax(-1).view(-1, 1, 1)
+        )
+        rj = (
+            (x == self.height * self.width).long().sum(dim=-2).argmax(-1).view(-1, 1, 1)
+        )
+
+        m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
+
         x = x.flatten(1)
-        u = torch.arange(self.height * self.width).reshape(1, -1)
-        m = ((x - u).abs() == 0).long()
-        d = (x - (m * u + (1 - m) * self.height * self.width)).abs().sum(-1) + (
-            m.sum(dim=-1) != self.height * self.width // 2
-        ).long()
+        u = torch.arange(self.height * self.width, device=x.device).reshape(1, -1)
+
+        d = (x - (m * u + (1 - m) * self.height * self.width)).abs().sum(-1)
         return d
 
     def moves(self, x):
@@ -376,7 +406,15 @@ class ProblemMixing(Problem):
         return " | ".join(
             [
                 " ".join(
-                    ["-".join([f"{x:02d}" for x in s]) for s in r.split(self.width)]
+                    [
+                        "-".join(
+                            [
+                                f"{x:02d}" if x < self.height * self.width else "**"
+                                for x in s
+                            ]
+                        )
+                        for s in r.split(self.width)
+                    ]
                 )
                 for r in seq.split(self.height * self.width)
             ]