def _step()

in gym/gym/envs/classic_control/cartpole.py [0:0]

• 31 lines of code
• 8 McCabe index (conditional complexity)

    def _step(self, action):
        assert self.action_space.contains(action), "%r (%s) invalid"%(action, type(action))
        state = self.state
        x, x_dot, theta, theta_dot = state
        force = self.force_mag if action==1 else -self.force_mag
        costheta = math.cos(theta)
        sintheta = math.sin(theta)
        temp = (force + self.polemass_length * theta_dot * theta_dot * sintheta) / self.total_mass
        thetaacc = (self.gravity * sintheta - costheta* temp) / (self.length * (4.0/3.0 - self.masspole * costheta * costheta / self.total_mass))
        xacc  = temp - self.polemass_length * thetaacc * costheta / self.total_mass
        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
        self.state = (x,x_dot,theta,theta_dot)
        done =  x < -self.x_threshold \
                or x > self.x_threshold \
                or theta < -self.theta_threshold_radians \
                or theta > self.theta_threshold_radians
        done = bool(done)

        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.warning("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, {}