snake2_env.py 文件源码

def step(self, action):
        self.forward_dynamics(action)
        next_obs = self.get_current_obs()
        lb, ub = self.action_bounds
        scaling = (ub - lb) * 0.5
        ctrl_cost = 0.5 * self.ctrl_cost_coeff * np.sum(
            np.square(action / scaling))
        forward_reward = np.linalg.norm(self.get_body_comvel("torso"))  # swimmer has no problem of jumping reward
        reward = forward_reward - ctrl_cost
        done = False
        if self.sparse_rew:
            if abs(self.get_body_com("torso")[0]) > 100.0:
                reward = 1.0
                done = True
            else:
                reward = 0.
        com = np.concatenate([self.get_body_com("torso").flat]).reshape(-1)
        ori = self.get_ori()
        return Step(next_obs, reward, done, com=com, ori=ori)