This program has been disqualified.
| Author | Sean |
| Submission date | 2016-09-01 22:46:51.960666 |
| Rating | 7298 |
| Matches played | 102 |
| Win rate | 73.53 |
if input == "":
import math
log = math.log
exp = math.exp
log_half = log(0.5)
third = 1.0 / 3.0
log_third = log(1.0/3.0)
log_two_thirds = log(2.0/3.0)
def to_probs(ps):
p0 = min(ps)
qs = [exp(p - p0) for p in ps]
rt = 1.0 / sum(qs)
for i, q in enumerate(qs):
qs[i] = q * rt
return qs
def log_add(x, y):
if y > x:
x, y = y, x
d = y - x
if d < -60:
return x
return x + log(1.0 + exp(d))
def log_sub(x, y):
d = y - x
return x + log(1.0 - exp(d))
def log_mean(x, y):
return log_half + log_add(x, y)
def log_mean_3(x, y, z):
return log_third + log_add(log_add(x, y), z)
class ContextTree:
def __init__(self):
self.p = 0.0
self.p_children = 0.0
self.weights = [log_third for _ in xrange(3)]
self.counts = [0, 0, 0]
self.meta_counts = [0, 0, 0]
self.cond = [third for _ in xrange(3)]
self.meta = [0 for _ in xrange(3)]
self.children = [None, None, None]
def update(self, depth, alpha, beta, history, c, i=0):
counts = self.counts
meta_counts = self.meta_counts
cond = self.cond
t = sum(counts)
rt = 1.0 / (t + 1.0)
if t:
p0 = min(cond)
scores = [exp(cond[beaten[j]] - p0) - exp(cond[beat[j]] - p0) for j in xrange(3)]
q = max(scores)
n = scores.count(q)
if n == 1:
k = scores.index(q)
d = (k + c) % 3
cond_p_meta = log((meta_counts[d] + third) * rt)
meta_counts[d] += 1
else:
cond_p_meta = log_third
else:
cond_p_meta = log_third
cond_p_self = log((counts[c] + third) * rt)
counts[c] += 1
if i >= min(len(history) - 1, depth):
self.p += cond_p_self
return
x = history[i]
if self.children[x] is None:
self.children[x] = ContextTree()
self.children[x].update(depth, alpha, beta, history, c, i + 1)
p_children = 0.0
for child in self.children:
if child is not None:
p_children += child.p
w0, w1, w2 = self.weights
cond_p_children = p_children - self.p_children
self.p_children = p_children
self.p = log_add(log_add(w0 + cond_p_self, w1 + cond_p_meta), w2 + cond_p_children)
probs = (cond_p_self, cond_p_meta, cond_p_children)
base = alpha + self.p
for i, (w, p) in enumerate(zip(self.weights, probs)):
self.weights[i] = log_add(base, beta + w + p)
def predict(self, depth, history, ps, i=0):
counts = self.counts
meta_counts = self.meta_counts
scores = [0.0 for _ in xrange(3)]
for j in xrange(3):
scores[j] = counts[beaten[j]] - counts[beat[j]]
q = max(scores)
n = scores.count(q)
rt = 1.0 / (sum(counts) + 1.0)
if n == 1:
k = scores.index(q)
cond_p_meta = (log((meta_counts[(k + c) % 3] + third) * rt) for c in xrange(3))
else:
cond_p_meta = (log_third for c in xrange(3))
cond_p_self = (log((counts[c] + third) * rt) for c in xrange(3))
if i >= min(len(history) - 1, depth):
for i, p0 in enumerate(cond_p_self):
ps[i] += p0 + self.p
return
x = history[i]
p_children = [0.0 for _ in self.children]
factor = 0.0
for y, child in enumerate(self.children):
if child is not None:
if y == x:
child.predict(depth, history, p_children, i + 1)
else:
factor += child.p
elif y == x:
factor += log_third
w0, w1, w2 = self.weights
w3 = w2 + factor - self.p_children
for i, (pse, pm, pc) in enumerate(zip(cond_p_self, cond_p_meta, p_children)):
self.cond[i] = log_add(w0 + pse, log_add(w1 + pm, w3 + pc))
for i in xrange(3):
ps[i] += self.cond[i]
import collections
import random
R, P, S = range(3)
index = {"R": R, "P": P, "S": S}
name = ("R", "P", "S")
beat = (P, S, R)
beaten = (S, R, P)
model = ContextTree()
my_model = ContextTree()
their_model = ContextTree()
history = collections.deque([])
my_history = collections.deque([])
their_history = collections.deque([])
output = random.choice(name)
rnd = 0
log_p = 0.0
weights = [log_third for _ in xrange(3)]
cond_ps = [[third for _ in xrange(3)] for _ in xrange(3)]
else:
inp = index[input]
out = index[output]
inp_ps = [w + log(p[inp]) for w, p in zip(weights, cond_ps)]
log_p = float("-inf")
for p in inp_ps:
log_p = log_add(log_p, p)
rnd += 1
alpha = 1.0 / (rnd + 2)
beta = 1 - 2 * alpha
alpha = log(alpha)
beta = log(beta)
base = alpha + log_p
for i, p in enumerate(inp_ps):
weights[i] = log_add(base, beta + p)
model.update(9, alpha, beta, history, inp)
my_model.update(3, alpha, beta, my_history, inp)
their_model.update(3, alpha, beta, their_history, inp)
history.appendleft(inp)
history.appendleft(out)
my_history.appendleft(out)
their_history.appendleft(inp)
ps = [0.0, 0.0, 0.0]
my_ps = [0.0, 0.0, 0.0]
their_ps = [0.0, 0.0, 0.0]
model.predict(9, history, ps)
my_model.predict(3, my_history, my_ps)
their_model.predict(3, their_history, their_ps)
cond_ps = [to_probs(p) for p in (ps, my_ps, their_ps)]
def get_ps():
for qs in zip(*cond_ps):
p = float("-inf")
for w, q in zip(weights, qs):
p = log_add(p, q)
yield p
ps = list(get_ps())
ps = to_probs(ps)
scores = [0, 0, 0]
for _ in xrange(3):
r = random.uniform(0, 1)
for k, p in enumerate(ps):
r -= p
if r <= 0:
break
scores[beat[k]] += 1
scores[beaten[k]] -= 1
m = max(scores)
output = name[random.choice([k for k, x in enumerate(scores) if x == m])]