Skip to content
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

Jump to bottom

Fixes problems in mdp.py #918

Merged
merged 2 commits into from
May 11, 2018
Merged

Fixes problems in mdp.py #918

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e13caa4
Added MDP2 class
ad71 Apr 30, 2018
176a49d
Updated loop termination condition in value_iteration
ad71 Apr 30, 2018
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
15 changes: 14 additions & 1 deletion mdp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,19 @@ def check_consistency(self):
assert abs(s - 1) < 0.001


class MDP2(MDP):

"""Inherits from MDP. Handles terminal states, and transitions to and from terminal states better."""
def __init__(self, init, actlist, terminals, transitions, reward=None, gamma=0.9):
MDP.__init__(self, init, actlist, terminals, transitions, reward, gamma=gamma)

def T(self, state, action):
if action is None:
return [(0.0, state)]
else:
return self.transitions[state][action]


class GridMDP(MDP):

"""A two-dimensional grid MDP, as in [Figure 17.1]. All you have to do is
Expand Down Expand Up @@ -186,7 +199,7 @@ def value_iteration(mdp, epsilon=0.001):
U1[s] = R(s) + gamma * max(sum(p*U[s1] for (p, s1) in T(s, a))
for a in mdp.actions(s))
delta = max(delta, abs(U1[s] - U[s]))
if delta < epsilon*(1 - gamma)/gamma:
if delta <= epsilon*(1 - gamma)/gamma:
return U


Expand Down