强化学习记录——gym中各种环境信息查看

from gym import envs
for env in envs.registry.all():
    print(env.id)

import gym
env = gym.make('Pendulum-v0')
for i_episode in range(20):
    observation = env.reset()
    for t in range(100):
        env.render()
        print(observation)
        action = env.action_space.sample()
        observation, reward, done, info = env.step(action)
        if done:
            print("Episode finished after {} timesteps".format(t+1))
            break
env.close()

import gym
env = gym.make('Pendulum-v0').unwrapped
print(env.action_space)  # 输出动作信息
#print(env.action_space.n)  # 输出动作个数
print(env.observation_space)  # 查看状态空间
print(env.observation_space.shape[0])  # 输出状态个数
print(env.observation_space.high)  # 查看状态的最高值
print(env.observation_space.low)  # 查看状态的最低值

经典控制环境Classic control:入门

算法学习环境Algorithms

2D仿真环境Box2D

Mujoco环境

Atari

文本游戏环境Toy text

五、官网提供

gym入门、环境鸟瞰图：Gym

环境脚本：gym/gym/envs/classic_control at master · openai/gym · GitHub