def __init__()

in gym/gym/envs/toy_text/taxi.py [0:0]

• 48 lines of code
• 24 McCabe index (conditional complexity)

    def __init__(self):
        self.desc = np.asarray(MAP,dtype='c')

        self.locs = locs = [(0,0), (0,4), (4,0), (4,3)]

        nS = 500
        nR = 5
        nC = 5
        maxR = nR-1
        maxC = nC-1
        isd = np.zeros(nS)
        nA = 6
        P = {s : {a : [] for a in range(nA)} for s in range(nS)}
        for row in range(5):
            for col in range(5):
                for passidx in range(5):
                    for destidx in range(4):
                        state = self.encode(row, col, passidx, destidx)
                        if passidx < 4 and passidx != destidx:
                            isd[state] += 1
                        for a in range(nA):
                            # defaults
                            newrow, newcol, newpassidx = row, col, passidx
                            reward = -1
                            done = False
                            taxiloc = (row, col)

                            if a==0:
                                newrow = min(row+1, maxR)
                            elif a==1:
                                newrow = max(row-1, 0)
                            if a==2 and self.desc[1+row,2*col+2]==b":":
                                newcol = min(col+1, maxC)
                            elif a==3 and self.desc[1+row,2*col]==b":":
                                newcol = max(col-1, 0)
                            elif a==4: # pickup
                                if (passidx < 4 and taxiloc == locs[passidx]):
                                    newpassidx = 4
                                else:
                                    reward = -10
                            elif a==5: # dropoff
                                if (taxiloc == locs[destidx]) and passidx==4:
                                    done = True
                                    reward = 20
                                elif (taxiloc in locs) and passidx==4:
                                    newpassidx = locs.index(taxiloc)
                                else:
                                    reward = -10
                            newstate = self.encode(newrow, newcol, newpassidx, destidx)
                            P[state][a].append((1.0, newstate, reward, done))
        isd /= isd.sum()
        discrete.DiscreteEnv.__init__(self, nS, nA, P, isd)