官术网_书友最值得收藏!

How it works...

Using Gym, we can easily create an environment instance by calling the make() method with the name of the environment as the parameter.

As you may have noticed, the actions that the agent performs are randomly chosen using the sample() method.

Note that, normally, we would have a more sophisticated agent guided by reinforcement learning algorithms. Here, we just demonstrated how to simulate an environment, and how an agent takes actions regardless of the outcome.

Run this a few times and see what we get:

>>> env.action_space.sample()
0
>>> env.action_space.sample()
3
>>> env.action_space.sample()
0
>>> env.action_space.sample()
4
>>> env.action_space.sample()
2
>>> env.action_space.sample()
1
>>> env.action_space.sample()
4
>>> env.action_space.sample()
5
>>> env.action_space.sample()
1
>>> env.action_space.sample()
0

There are six possible actions in total. We can also see this by running the following command:

>>> env.action_space
Discrete(6)

Actions from 0 to 5 stand for No Operation, Fire, Up, Right, Left, and Down, respectively, which are all the moves the spaceship in the game can do.

The step() method will let the agent take the action that is specified as its parameter. The render() method will update the display window based on the latest observation of the environment.

The observation of the environment, new_state, is represented by a 210 x 160 x 3 matrix, as follows:

>>> print(new_state.shape)
(210, 160, 3)

This means that each frame of the display screen is an RGB image of size 210 x 160.

主站蜘蛛池模板: 大同县| 贞丰县| 虎林市| 方城县| 南通市| 三亚市| 乐都县| 治县。| 姚安县| 南和县| 六安市| 乐山市| 临洮县| 喜德县| 青河县| 苏尼特左旗| 鄂伦春自治旗| 清远市| 布拖县| 元朗区| 阿合奇县| 巴彦淖尔市| 桐庐县| 铜陵市| 宣城市| 明光市| 广西| 滦南县| 萨嘎县| 汉川市| 安化县| 靖江市| 互助| 沈阳市| 伽师县| 河源市| 苏尼特右旗| 稻城县| 利津县| 墨江| 信宜市|