$ pip install chainerrl
import chainer
import chainer.functions as F
import chainer.links as L
import chainerrl
import gym
import numpy as np
env = gym.make('CartPole-v0')
print('observation space:', env.observation_space)
print('action space:', env.action_space)
obs = env.reset()
env.render()
print('initial observation:', obs)
action = env.action_space.sample()
obs, r, done, info = env.step(action)
$ pip install chainerrl
import chainer
import chainer.functions as F
import chainer.links as L
import chainerrl
import gym
import numpy as np
env = gym.make('CartPole-v0')
print('observation space:', env.observation_space)
print('action space:', env.action_space)
obs = env.reset()
env.render()
print('initial observation:', obs)
action = env.action_space.sample()
obs, r, done, info = env.step(action)