multiagent/scenarios/simple_tag.py [53:87]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                landmark.state.p_pos = np.random.uniform(-0.9, +0.9, world.dim_p)
                landmark.state.p_vel = np.zeros(world.dim_p)


    def benchmark_data(self, agent, world):
        # returns data for benchmarking purposes
        if agent.adversary:
            collisions = 0
            for a in self.good_agents(world):
                if self.is_collision(a, agent):
                    collisions += 1
            return collisions
        else:
            return 0


    def is_collision(self, agent1, agent2):
        delta_pos = agent1.state.p_pos - agent2.state.p_pos
        dist = np.sqrt(np.sum(np.square(delta_pos)))
        dist_min = agent1.size + agent2.size
        return True if dist < dist_min else False

    # return all agents that are not adversaries
    def good_agents(self, world):
        return [agent for agent in world.agents if not agent.adversary]

    # return all adversarial agents
    def adversaries(self, world):
        return [agent for agent in world.agents if agent.adversary]


    def reward(self, agent, world):
        # Agents are rewarded based on minimum agent distance to each landmark
        main_reward = self.adversary_reward(agent, world) if agent.adversary else self.agent_reward(agent, world)
        return main_reward
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



multiagent/scenarios/simple_world_comm.py [112:146]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            landmark.state.p_pos = np.random.uniform(-0.9, +0.9, world.dim_p)
            landmark.state.p_vel = np.zeros(world.dim_p)

    def benchmark_data(self, agent, world):
        if agent.adversary:
            collisions = 0
            for a in self.good_agents(world):
                if self.is_collision(a, agent):
                    collisions += 1
            return collisions
        else:
            return 0


    def is_collision(self, agent1, agent2):
        delta_pos = agent1.state.p_pos - agent2.state.p_pos
        dist = np.sqrt(np.sum(np.square(delta_pos)))
        dist_min = agent1.size + agent2.size
        return True if dist < dist_min else False


    # return all agents that are not adversaries
    def good_agents(self, world):
        return [agent for agent in world.agents if not agent.adversary]

    # return all adversarial agents
    def adversaries(self, world):
        return [agent for agent in world.agents if agent.adversary]


    def reward(self, agent, world):
        # Agents are rewarded based on minimum agent distance to each landmark
        #boundary_reward = -10 if self.outside_boundary(agent) else 0
        main_reward = self.adversary_reward(agent, world) if agent.adversary else self.agent_reward(agent, world)
        return main_reward
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -