def _comp_move_reward()

in robosumo/envs/sumo.py [0:0]

• 5 lines of code
• 1 McCabe index (conditional complexity)

    def _comp_move_reward(self, agent, target):
        move_vec = (agent.posafter - agent.posbefore) / self.dt
        direction = target - agent.posbefore
        direction /= np.linalg.norm(direction)
        return max(np.sum(move_vec * direction), 0.) * self.MOVE_TO_OPP_COEF