def goal_rewards()

in gym-compete/gym_compete/new_envs/sumo.py [0:0]

• 34 lines of code
• 16 McCabe index (conditional complexity)

    def goal_rewards(self, infos=None, agent_dones=None):
        self._elapsed_steps += 1
        goal_rews = [0. for _ in range(self.n_agents)]
        fallen = [self._is_fallen(i)
                  for i in range(self.n_agents)]

        timeup = self._past_limit()
        past_arena = [self._past_arena(i) for i in range(self.n_agents)]
        done = False

        agent_contacts = self.get_agent_contacts()
        if len(agent_contacts) > 0:
            # print('Detected contacts:', agent_contacts)
            self.agent_contacts = True

        if any(fallen):
            done = True
            for j in range(self.n_agents):
                if fallen[j]:
                    print('Agent', j, 'fallen')
                    goal_rews[j] -= self.GOAL_REWARD
                elif self.agent_contacts:
                    goal_rews[j] += self.GOAL_REWARD
                    infos[j]['winner'] = True
            # import ipdb; ipdb.set_trace()
        elif any(past_arena):
            done = True
            for j in range(self.n_agents):
                if past_arena[j]:
                    print('Agent', j, 'past arena')
                    goal_rews[j] -= self.GOAL_REWARD
                elif self.agent_contacts:
                    goal_rews[j] += self.GOAL_REWARD
                    infos[j]['winner'] = True
        elif timeup:
            for j in range(self.n_agents):
                goal_rews[j] -= self.GOAL_REWARD

        done = timeup or done

        return goal_rews, done