Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Consistent Variable Naming #220

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 12, 2016
Merged

Consistent Variable Naming #220

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6655a02
Change variable names from s_prime to s1, current_state to s1
reachtarunhere Apr 12, 2016
cb322db
Sane default for update_state
reachtarunhere Apr 12, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions rl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,18 +39,18 @@ def __init__(self, pi, mdp, alpha=None):
self.alpha = lambda n: 1./(1+n) # udacity video

def __call__(self, percept):
s_prime, r_prime = self.update_state(percept)
s1, r1 = self.update_state(percept)
pi, U, Ns, s, a, r = self.pi, self.U, self.Ns, self.s, self.a, self.r
alpha, gamma, terminals = self.alpha, self.gamma, self.terminals
if not Ns[s_prime]:
U[s_prime] = r_prime
if not Ns[s1]:
U[s1] = r1
if s is not None:
Ns[s] += 1
U[s] += alpha(Ns[s]) * (r + gamma * U[s_prime] - U[s])
if s_prime in terminals:
U[s] += alpha(Ns[s]) * (r + gamma * U[s1] - U[s])
if s1 in terminals:
self.s = self.a = self.r = None
else:
self.s, self.a, self.r = s_prime, pi[s_prime], r_prime
self.s, self.a, self.r = s1, pi[s1], r1
return self.a

def update_state(self, percept):
Expand Down
29 changes: 15 additions & 14 deletions search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -437,34 +437,35 @@ def __init__(self, problem):
self.result = {}

def __call__(self, percept):
current_state = self.update_state(percept)
if self.problem.goal_test(current_state):
s1 = self.update_state(percept)
if self.problem.goal_test(s1):
self.a = None
else:
if current_state not in self.untried.keys():
self.untried[current_state] = self.problem.actions(
current_state)
if s1 not in self.untried.keys():
self.untried[s1] = self.problem.actions(s1)
if self.s is not None:
if current_state != self.result[(self.s, self.a)]:
self.result[(self.s, self.a)] = current_state
unbacktracked[current_state].insert(0, self.s)
if len(self.untried[current_state]) == 0:
if len(self.unbacktracked[current_state]) == 0:
if s1 != self.result[(self.s, self.a)]:
self.result[(self.s, self.a)] = s1
unbacktracked[s1].insert(0, self.s)
if len(self.untried[s1]) == 0:
if len(self.unbacktracked[s1]) == 0:
self.a = None
else:
# else a <- an action b such that result[s', b] = POP(unbacktracked[s']) # noqa
unbacktracked_pop = self.unbacktracked[current_state].pop(0) # noqa
unbacktracked_pop = self.unbacktracked[s1].pop(0) # noqa
for (s, b) in self.result.keys():
if self.result[(s, b)] == unbacktracked_pop:
self.a = b
break
else:
self.a = self.untried[current_state].pop(0)
self.s = current_state
self.a = self.untried[s1].pop(0)
self.s = s1
return self.a

def update_state(self, percept):
raise NotImplementedError
''' To be overriden in most cases. The default case
assumes th percept to be of type state'''
raise percept

# ______________________________________________________________________________

Expand Down