वर्ल्ड मॉडल्स: दुनिया कैसे चलती है, यह सीखना

import random
from collections import Counter, defaultdict, deque

# The real world (the robot cannot see this code, it can only try actions).
SIZE, WALLS = 4, {(1, 1), (2, 1)}
MOVES = {"up": (-1, 0), "down": (1, 0), "left": (0, -1), "right": (0, 1)}

def real_world(state, action):
    r, c = state[0] + MOVES[action][0], state[1] + MOVES[action][1]
    if not (0 <= r < SIZE and 0 <= c < SIZE) or (r, c) in WALLS:
        return state
    return (r, c)

# 1. Explore at random and record what happened: (state, action) -> next state.
random.seed(0)
seen = defaultdict(Counter)
s = (0, 0)
for _ in range(2000):
    a = random.choice(list(MOVES))
    s2 = real_world(s, a)
    seen[(s, a)][s2] += 1
    s = s2

# 2. The learned world model: predict the most common outcome we saw.
def model(state, action):
    outcomes = seen.get((state, action))
    return outcomes.most_common(1)[0][0] if outcomes else None  # None = "never tried"

# 3. Plan inside the model only (breadth-first search), no real moves needed.
def plan(start, goal):
    frontier, came_from = deque([start]), {start: None}
    while frontier:
        s = frontier.popleft()
        if s == goal:
            steps = []
            while came_from[s]:
                s, a = came_from[s]
                steps.append(a)
            return steps[::-1]
        for a in MOVES:
            nxt = model(s, a)
            if nxt is not None and nxt not in came_from:
                came_from[nxt] = (s, a)
                frontier.append(nxt)
    return None

actions = plan((0, 0), (3, 3))
print("Plan made inside the model:", actions)

# 4. Check the plan in the real world.
s = (0, 0)
for a in actions:
    s = real_world(s, a)
print("Real world ends at:", s)