-class ProblemTwoCuts(Problem):
- def __init__(self, len_total=50, nb_values=100, global_constraint=True):
- self.len_total = len_total
- self.nb_values = nb_values
- self.global_constraint = global_constraint
-
- def generate_sequences_internal(self, nb):
- return u,v,a,b,c
-
- def generate_sequences(self,nb):
-
- u = torch.randint(self.len_total, (nb,))
- v = torch.randint(self.len_total, (nb,))
-
- a = torch.randint(self.nb_values, (nb,))
- b = torch.randint(self.nb_values, (nb,))
- c = torch.randint(self.nb_values, (nb,))
-
- while True:
- to_compute = torch.logical_or(u>=v-self.len_total//10,u<v-self.len_total//5)
- to_compute =torch.logical_or(to_compute, u == 0)
- to_compute =torch.logical_or(to_compute, v == self.len_total)
- n = to_compute.long().sum()
- if n == 0:
- break
- else:
- u[to_compute] = torch.randint(self.len_total, (n,))
- v[to_compute] = torch.randint(self.len_total, (n,))
-
- while True:
- to_compute = a==b
- to_compute = torch.logical_or(to_compute,b==c)
- to_compute = torch.logical_or(to_compute,a==c)
-
- if self.global_constraint:
- to_compute = torch.logical_or(to_compute,(a*u+b*(v-u)+c*(self.len_total-v)) // self.len_total != self.nb_values//2)
-
- n = to_compute.long().sum()
- if n == 0:
- break
- else:
- a[to_compute] = torch.randint(self.nb_values, (n,))
- b[to_compute] = torch.randint(self.nb_values, (n,))
- c[to_compute] = torch.randint(self.nb_values, (n,))
-
- assert (u>=v).long().sum() == 0
- assert (a==b).long().sum() == 0
- assert (a==c).long().sum() == 0
- assert (c==b).long().sum() == 0
-
- t = torch.arange(self.len_total)
- seq = (t[None,:] < u[:,None]).long() * a[:,None] + \
- (t[None,:] >= u[:,None]).long() * (t[None,:] < v[:,None]).long() * b[:,None] + \
- (t[None,:] >= v[:,None]).long() * c[:,None]
-
- return seq,seq.new_full(seq.size(), 1, dtype=torch.int64)
+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
+ self.nb_state_tokens = nb_state_tokens
+ self.nb_time_steps = nb_time_steps
+ self.value_max = value_max
+ self.hard = hard
+
+ def generate_sequences(self, nb):
+ x = (
+ torch.rand(nb, self.nb_state_tokens).sort(dim=-1).indices == 0
+ ).long() * self.value_max
+ seq = [x]
+
+ for t in range(self.nb_time_steps - 1):
+ v = (torch.rand(x.size()).sort(dim=-1).indices + 1) * (x >= 2).long()
+ u = (v.max(dim=-1, keepdim=True).values == v).long()
+ n = (
+ (u * x)
+ .minimum(2 + torch.randint(self.value_max // 4 - 2, x.size()))
+ .sum(dim=-1, keepdim=True)
+ )
+ m = 1 + ((n - 1) * torch.rand(n.size())).long()
+ x = (
+ x
+ + m * u.roll(shifts=-1, dims=-1)
+ - n * u
+ + (n - m) * u.roll(shifts=1, dims=-1)
+ )
+ seq.append(x)
+
+ if self.hard:
+ seq.reverse()
+
+ seq = torch.cat(seq, dim=1)
+ return seq, seq.new_full(seq.size(), 1, dtype=torch.int64)