def step()

in gym/envs/mujoco/ant.py [0:0]

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

    def step(self, a):
        xposbefore = self.get_body_com("torso")[0]
        self.do_simulation(a, self.frame_skip)
        xposafter = self.get_body_com("torso")[0]

        forward_reward = (xposafter - xposbefore) / self.dt
        ctrl_cost = 0.5 * np.square(a).sum()
        contact_cost = (
            0.5 * 1e-3 * np.sum(np.square(np.clip(self.sim.data.cfrc_ext, -1, 1)))
        )
        survive_reward = 1.0
        reward = forward_reward - ctrl_cost - contact_cost + survive_reward
        state = self.state_vector()
        not_terminated = (
            np.isfinite(state).all() and state[2] >= 0.2 and state[2] <= 1.0
        )
        terminated = not not_terminated
        ob = self._get_obs()

        if self.render_mode == "human":
            self.render()
        return (
            ob,
            reward,
            terminated,
            False,
            dict(
                reward_forward=forward_reward,
                reward_ctrl=-ctrl_cost,
                reward_contact=-contact_cost,
                reward_survive=survive_reward,
            ),
        )