cartpole源代码

cartpole源代码

在上面代码中使用了env.step()函数来对每一步进行仿真，在Gym中，env.step()会返回 4 个参数：

观测 Observation (Object)：当前step执行后，环境的观测(类型为对象)。例如，从相机获取的像素点，机器人各个关节的角度或棋盘游戏当前的状态等；
奖励 Reward (Float): 执行上一步动作(action)后，智能体( agent)获得的奖励(浮点类型)，不同的环境中奖励值变化范围也不相同，但是强化学习的目标就是使得总奖励值最大；
完成 Done (Boolen): 表示是否需要将环境重置 env.reset。大多数情况下，当 Done 为True 时，就表明当前回合(episode)或者试验(tial)结束。例如当机器人摔倒或者掉出台面，就应当终止当前回合进行重置(reset);
信息 Info (Dict): 针对调试过程的诊断信息。在标准的智体仿真评估当中不会使用到这个info，具体用到的时候再说。
在 Gym 仿真中，每一次回合开始，需要先执行 reset() 函数，返回初始观测信息，然后根据标志位 done 的状态，来决定是否进行下一次回合。所以更恰当的方法是遵守done的标志，当done 为真时，控制失败，此阶段episode 结束。

"""
Classic cart-pole system implemented by Rich Sutton et al.
Copied from http://incompleteideas.net/sutton/book/code/pole.c
permalink: https://perma.cc/C9ZM-652R
"""

import math
import gym
from gym import spaces, logger
from gym.utils import seeding
import numpy as np


class CartPoleEnv(gym.Env):
    """
    Description:
        A pole is attached by an un-actuated joint to a cart, which moves along
        a frictionless track. The pendulum starts upright, and the goal is to
        prevent it from falling over by increasing and reducing the cart's
        velocity.
    Source:
        This environment corresponds to the version of the cart-pole problem
        described by Barto, Sutton, and Anderson
    Observation:
        Type: Box(4)
        Num	Observation               Min             Max
        0	Cart Position             -4.8            4.8
        1	Cart Velocity             -Inf            Inf
        2	Pole Angle                -24 deg         24 deg
        3	Pole Velocity At Tip      -Inf            Inf
    Actions:
        Type: Discrete(2)
        Num	Action
        0	Push cart to the left
        1	Push cart to the right
        Note: The amount the velocity that is reduced or increased is not
        fixed; it depends on the angle the pole is pointing. This is because
        the center of gravity of the pole increases the amount of energy needed
        to move the cart underneath it
    Reward:
        Reward is 1 for every step taken, including the termination step
    Starting State:
        All observations are assigned a uniform random value in [-0.05..0.05]
    Episode Termination:
        Pole Angle is more than 12 degrees.
        Cart Position is more than 2.4 (center of the cart reaches the edge of
        the display).
        Episode length is greater than 200.
        Solved Requirements:
        Considered solved when the average reward is greater than or equal to
        195.0 over 100 consecutive trials.
    """

    metadata = {
        'render.modes': ['human', 'rgb_array'],
        'video.frames_per_second': 50
    }

    def __init__(self):
        self.gravity = 9.8
        self.masscart = 1.0
        self.masspole = 0.1
        self.total_mass = (self.masspole + self.masscart)
        self.length = 0.5  # actually half the pole's length
        self.polemass_length = (self.masspole * self.length)
        self.force_mag = 10.0
        self.tau = 0.02  # seconds between state updates
        self.kinematics_integrator = 'euler'

        # Angle at which to fail the episode
        self.theta_threshold_radians = 12 * 2 * math.pi / 360
        self.x_threshold = 2.4

        # Angle limit set to 2 * theta_threshold_radians so failing observation
        # is still within bounds.
        high = np.array([self.x_threshold * 2,
                         np.finfo(np.float32).max,
                         self.theta_threshold_radians * 2,
                         np.finfo(np.float32).max],
                        dtype=np.float32)

        self.action_space = spaces.Discrete(2)
        self.observation_space = spaces.Box(-high, high, dtype=np.float32)

        self.seed()
        self.viewer = None
        self.state = None

        self.steps_beyond_done = None

    def seed(self, seed=None):
        self.np_random, seed = seeding.np_random(seed)
        return [seed]

    def step(self, action):
        err_msg = "%r (%s) invalid" % (action, type(action))
        assert self.action_space.contains(action), err_msg

        x, x_dot, theta, theta_dot = self.state
        force = self.force_mag if action == 1 else -self.force_mag
        costheta = math.cos(theta)
        sintheta = math.sin(theta)

        # For the interested reader:
        # https://coneural.org/florian/papers/05_cart_pole.pdf
        temp = (force + self.polemass_length * theta_dot ** 2 * sintheta) / self.total_mass
        thetaacc = (self.gravity * sintheta - costheta * temp) / (self.length * (4.0 / 3.0 - self.masspole * costheta ** 2 / self.total_mass))
        xacc = temp - self.polemass_length * thetaacc * costheta / self.total_mass

        if self.kinematics_integrator == 'euler':
            x = x + self.tau * x_dot
            x_dot = x_dot + self.tau * xacc
            theta = theta + self.tau * theta_dot
            theta_dot = theta_dot + self.tau * thetaacc
        else:  # semi-implicit euler
            x_dot = x_dot + self.tau * xacc
            x = x + self.tau * x_dot
            theta_dot = theta_dot + self.tau * thetaacc
            theta = theta + self.tau * theta_dot

        self.state = (x, x_dot, theta, theta_dot)

        done = bool(
            x < -self.x_threshold
            or x > self.x_threshold
            or theta < -self.theta_threshold_radians
            or theta > self.theta_threshold_radians
        )

        if not done:
            reward = 1.0
        elif self.steps_beyond_done is None:
            # Pole just fell!
            self.steps_beyond_done = 0
            reward = 1.0
        else:
            if self.steps_beyond_done == 0:
                logger.warn(
                    "You are calling 'step()' even though this "
                    "environment has already returned done = True. You "
                    "should always call 'reset()' once you receive 'done = "
                    "True' -- any further steps are undefined behavior."
                )
            self.steps_beyond_done += 1
            reward = 0.0

        return np.array(self.state), reward, done, {}

    def reset(self):
        self.state = self.np_random.uniform(low=-0.05, high=0.05, size=(4,))
        self.steps_beyond_done = None
        return np.array(self.state)

    def render(self, mode='human'):
        screen_width = 600
        screen_height = 400

        world_width = self.x_threshold * 2
        scale = screen_width/world_width
        carty = 100  # TOP OF CART
        polewidth = 10.0
        polelen = scale * (2 * self.length)
        cartwidth = 50.0
        cartheight = 30.0

        if self.viewer is None:
            from gym.envs.classic_control import rendering
            self.viewer = rendering.Viewer(screen_width, screen_height)
            l, r, t, b = -cartwidth / 2, cartwidth / 2, cartheight / 2, -cartheight / 2
            axleoffset = cartheight / 4.0
            cart = rendering.FilledPolygon([(l, b), (l, t), (r, t), (r, b)])
            self.carttrans = rendering.Transform()
            cart.add_attr(self.carttrans)
            self.viewer.add_geom(cart)
            l, r, t, b = -polewidth / 2, polewidth / 2, polelen - polewidth / 2, -polewidth / 2
            pole = rendering.FilledPolygon([(l, b), (l, t), (r, t), (r, b)])
            pole.set_color(.8, .6, .4)
            self.poletrans = rendering.Transform(translation=(0, axleoffset))
            pole.add_attr(self.poletrans)
            pole.add_attr(self.carttrans)
            self.viewer.add_geom(pole)
            self.axle = rendering.make_circle(polewidth/2)
            self.axle.add_attr(self.poletrans)
            self.axle.add_attr(self.carttrans)
            self.axle.set_color(.5, .5, .8)
            self.viewer.add_geom(self.axle)
            self.track = rendering.Line((0, carty), (screen_width, carty))
            self.track.set_color(0, 0, 0)
            self.viewer.add_geom(self.track)

            self._pole_geom = pole

        if self.state is None:
            return None

        # Edit the pole polygon vertex
        pole = self._pole_geom
        l, r, t, b = -polewidth / 2, polewidth / 2, polelen - polewidth / 2, -polewidth / 2
        pole.v = [(l, b), (l, t), (r, t), (r, b)]

        x = self.state
        cartx = x[0] * scale + screen_width / 2.0  # MIDDLE OF CART
        self.carttrans.set_translation(cartx, carty)
        self.poletrans.set_rotation(-x[2])

        return self.viewer.render(return_rgb_array=mode == 'rgb_array')

    def close(self):
        if self.viewer:
            self.viewer.close()
            self.viewer = None

转自：https://github.com/openai/gym/blob/master/gym/envs/classic_control/cartpole.py
ttps://blog.csdn.net/qq_32892383/article/details/89576003