def reward()

in multiagent/scenarios/simple_spread.py [0:0]

• 10 lines of code
• 7 McCabe index (conditional complexity)

    def reward(self, agent, world):
        # Agents are rewarded based on minimum agent distance to each landmark, penalized for collisions
        rew = 0
        for l in world.landmarks:
            dists = [np.sqrt(np.sum(np.square(a.state.p_pos - l.state.p_pos))) for a in world.agents]
            rew -= min(dists)
        if agent.collide:
            for a in world.agents:
                if self.is_collision(a, agent):
                    rew -= 1
        return rew