# [MountainCar-v0](https://gym.openai.com/envs/MountainCar-v0/)

 
 
**Environment :**
 
 

 
 
**Reward :**
每走一步都會減少 1 分 ， 直到到達目標點為止 (position 0.5)

 
 
**Starting State :**
初始位置為 positon : -0.6 ~ -0.4 ， 且速度 (velocity) 為 0
 
 
**Episode Termination :**
當你到達目標點或是移動了250步之後 ， episode 結束
 
 
 
 

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

import gym

env = gym.make("MountainCar-v0")
env.reset()

plt.imshow(env.render('rgb_array'))
print("Observation space:", env.observation_space)
print("Action space:", env.action_space)

 
Observation space: Box(2,)
Action space: Discrete(3)


 
 

obs0 = env.reset()
print("initial observation code:", obs0)

# Note: in MountainCar, observation is just two numbers: car position and velocity

 
initial observation code: [-0.42123736 0. ]
 
 

print("taking action 2 (right)")
new_obs, reward, is_done, _ = env.step(2)

print("new observation code:", new_obs)
print("reward:", reward)
print("is game over?:", is_done)

# Note: as you can see, the car has moved to the right slightly (around 0.0005)

 
taking action 2 (right)
new observation code: [-4.20993065e-01 2.44298593e-04]
reward: -1.0
is game over?: False

 
 
 
 
Hint: your action at each step should depend either on t or on s.

from IPython import display

# create env manually to set time limit. Please don't change this.
TIME_LIMIT = 250
env = gym.wrappers.TimeLimit(
    gym.envs.classic_control.MountainCarEnv(),
    max_episode_steps=TIME_LIMIT + 1,
)
s = env.reset()
actions = {'left': 0, 'stop': 1, 'right': 2}

plt.figure(figsize=(4, 3))
display.clear_output(wait=True)

for t in range(TIME_LIMIT):
    plt.gca().clear()
    
    # change the line below to reach the flag
    if t>50 and t<100:
        s, r, done, _ = env.step(actions['left'])
    else:
        s, r, done, _ = env.step(actions['right'])

    # draw game image on display
    plt.imshow(env.render('rgb_array'))
    
    display.clear_output(wait=True)
    display.display(plt.gcf())

    if done:
        print("Well done!")
        break
else:
    print("Time limit exceeded. Try again.")

display.clear_output(wait=True)


 
 

assert s[0] > 0.47
print("You solved it!")

 
You solved it!

 
 
 
 
 
 
 
 
time_limit.py

import gym


class TimeLimit(gym.Wrapper):
    def __init__(self, env, max_episode_steps=None):
        super(TimeLimit, self).__init__(env)
        if max_episode_steps is None:
            max_episode_steps = env.spec.max_episode_steps
        self.env.spec.max_episode_steps = max_episode_steps
        self._max_episode_steps = max_episode_steps
        self._elapsed_steps = None

    def step(self, action):
        assert self._elapsed_steps is not None, "Cannot call env.step() before calling reset()"
        observation, reward, done, info = self.env.step(action)
        self._elapsed_steps += 1
        if self._elapsed_steps >= self._max_episode_steps:
            info['TimeLimit.truncated'] = not done
            done = True
        return observation, reward, done, info

    def reset(self, **kwargs):
        self._elapsed_steps = 0
        return self.env.reset(**kwargs)