####################
+
+
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
####################
+class ProblemMemory(Problem):
+ def __init__(self, len_total=25):
+ self.len_total = len_total
+ self.max_len_pattern = 5
+ self.nb_noise_tokens = 10
+ self.start_pattern_token = 0
+ self.end_pattern_token = 1
+ self.start_result_token = 2
+ self.end_result_token = 3
+ self.token_string = "[]<>" + "".join(
+ [chr(ord("a") + k) for k in range(self.nb_noise_tokens)]
+ )
+
+ def generate_sequences(self, nb):
+ sequences = (
+ torch.randint(self.nb_noise_tokens, (nb, self.len_total))
+ + self.end_result_token
+ + 1
+ )
+ len_patterns = torch.randint(self.max_len_pattern, (nb,)) + 1
+ pattern_positions = torch.randint(
+ self.len_total - (5 + 2 * self.max_len_pattern), (nb,)
+ )
+ k = self.len_total - (3 + self.max_len_pattern)
+ for i in range(nb):
+ l = len_patterns[i]
+ j = pattern_positions[i]
+ sequences[i, j] = self.start_pattern_token
+ sequences[i, j + l + 2] = self.end_pattern_token
+ sequences[i, k] = self.start_result_token
+ sequences[i, k + l + 2] = self.end_result_token
+ sequences[i, k + 1 : k + 2 + l] = sequences[i, j + 1 : j + 2 + l]
+
+ j = torch.arange(self.len_total)[None, :]
+ ar_mask = (j > k).long() * (j <= k + 1 + len_patterns[:, None]).long()
+
+ return sequences, ar_mask
+
+ def seq2str(self, seq):
+ return "".join(self.token_string[x.item()] for x in seq)
+
+
class ProblemTwoTargets(Problem):
def __init__(self, len_total=10, len_targets=3):
assert len_targets >= 3
class ProblemMixing(Problem):
- def __init__(self, height=4, width=4, nb_time_steps=9, 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)
+ )
- 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)
- ri = torch.randint(self.height, (nb,)).reshape(nb,1,1)
- rj = torch.randint(self.width, (nb,)).reshape(nb,1,1)
+ m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
- m = 1 - torch.logical_or(i==ri,j==rj).long().flatten(1)
+ y = y * m + self.height * self.width * (1 - m)
- y = (y * m + self.height * self.width * (1 - m)).reshape(
- nb, self.height, self.width
- )
+ 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)
+ if self.random_start:
+ 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)
+ m = 1 - torch.logical_or(i == ri, j == rj).long().flatten(1)
+ else:
+ m = 1
x = x.flatten(1)
- u = torch.arange(self.height * self.width, device = x.device).reshape(1, -1)
+ 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):
return " | ".join(
[
" ".join(
- ["-".join([f"{x:02d}" if x < self.height * self.width else "**" 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)
]
####################
if __name__ == "__main__":
- p = ProblemMixing()
+ p = ProblemMixing(height=3, width=3, random_start=False)
+
s, m = p.generate_sequences(10000)
for x in s[:5]:
print(p.seq2str(x))
projects / picoclvr.git / blobdiff