Convert mdp.py to third edition.

darius · darius · commit 8588d0c536db · 2011-11-01T07:46:02.000Z
diff --git a/mdp.py b/mdp.py
@@ -6,19 +6,16 @@
 dictionary of {state:number} pairs.  We then define the value_iteration
 and policy_iteration algorithms."""
 
-# (Written for the second edition of AIMA; expect some discrepanciecs
-# from the third edition until this gets reviewed.)
-
 from utils import *
 
 class MDP:
     """A Markov Decision Process, defined by an initial state, transition model,
     and reward function. We also keep track of a gamma value, for use by
     algorithms. The transition model is represented somewhat differently from
-    the text.  Instead of T(s, a, s') being a probability number for each
-    state/action/state triplet, we instead have T(s, a) return a list of (p, s')
+    the text.  Instead of P(s' | s, a) being a probability number for each
+    state/state/action triplet, we instead have T(s, a) return a list of (p, s')
     pairs.  We also keep track of the possible states, terminal states, and
-    actions for each state. [page 615]"""
+    actions for each state. [page 646]"""
 
     def __init__(self, init, actlist, terminals, gamma=.9):
         update(self, init=init, actlist=actlist, terminals=terminals,
