在强化学习中,多智能体系统涉及到多个智能体相互作用的情况。在本篇博客中,我们将介绍如何在 OpenAI Gym 中构建和训练多智能体系统,并使用 Multi-Agent Deep Deterministic Policy Gradients(MADDPG)算法进行协同训练。
首先,确保你已经安装了 OpenAI Gym 和其他必要的依赖:
pip install gym
pip install numpy
pip install tensorflow
pip install matplotlib
我们将以一个简单的多智能体环境为例,该环境称为 MultiAgentEnv,其中包含两个智能体,它们分别控制两辆小车,目标是使两辆小车在一个二维平面上协同移动,避免相互碰撞。
import gym
from gym import spaces
import numpy as np
class MultiAgentEnv(gym.Env):
def __init__(self):
super(MultiAgentEnv, self).__init__()
# 定义动作空间和观察空间
self.action_space = spaces.Discrete(5) # 5个离散动作
self.observation_space = spaces.Box(low=0, high=1, shape=(4,), dtype=np.float32) # 连续观察空间,包含4个状态
# 初始化两辆小车的状态
self.agent1_state = np.array([0.2, 0.5, 0.0, 0.0])
self.agent2_state = np.array([0.8, 0.5, 0.0, 0.0])
def reset(self):
# 重置环境,将两辆小车放置在初始位置
self.agent1_state = np.array([0.2, 0.5, 0.0, 0.0])
self.agent2_state = np.array([0.8, 0.5, 0.0, 0.0])
return np.concatenate([self.agent1_state, self.agent2_state])
def step(self, actions):
# 执行动作,更新两辆小车的状态并返回奖励和观察结果
self.agent1_state[0] += 0.1 * (actions[0] - 2)
self.agent1_state[1] += 0.1 * (actions[1] - 2)
self.agent2_state[0] += 0.1 * (actions[2] - 2)
self.agent2_state[1] += 0.1 * (actions[3] - 2)
# 规定状态范围在 [0, 1] 之间
self.agent1_state[:2] = np.clip(self.agent1_state[:2], 0, 1)
self.agent2_state[:2] = np.clip(self.agent2_state[:2], 0, 1)
# 计算奖励
reward1 = -np.linalg.norm(self.agent1_state[:2] - self.agent2_state[:2])
reward2 = -np.linalg.norm(self.agent2_state[:2] - self.agent1_state[:2])
# 返回观察结果、奖励、是否终止和其他信息
return np.concatenate([self.agent1_state, self.agent2_state]), [reward1, reward2], False, {}
接下来,我们将实现 MADDPG 算法。为了简化,我们将只实现两个智能体的情况。
import tensorflow as tf
from tensorflow.keras import layers
class ActorCritic(tf.keras.Model):
def __init__(self, num_actions):
super(ActorCritic, self).__init__()
# 定义Actor网络
self.actor_fc1 = layers.Dense(64, activation='relu')
self.actor_fc2 = layers.Dense(64, activation='relu')
self.actor_output = layers.Dense(num_actions, activation='softmax')
# 定义Critic网络
self.critic_fc1 = layers.Dense(64, activation='relu')
self.critic_fc2 = layers.Dense(64, activation='relu')
self.critic_output = layers.Dense(1, activation='linear')
def call(self, state):
# Actor网络输出动作概率
actor_x = self.actor_fc1(state)
actor_x = self.actor_fc2(actor_x)
action_probs = self.actor_output(actor_x)
# Critic网络输出状态值
critic_x = self.critic_fc1(state)
critic_x = self.critic_fc2(critic_x)
state_value = self.critic_output(critic_x)
return action_probs, state_value
现在,我们将使用 MADDPG 算法来训练多智能体系统。
def train_maddpg(env, model1, model2, optimizer1, optimizer2, num_episodes=1000, gamma=0.99):
for episode in range(num_episodes):
state = env.reset()
state = tf.convert_to_tensor(state, dtype=tf.float32)
total_reward1 = 0
total_reward2 = 0
with tf.GradientTape() as tape1, tf.GradientTape() as tape2:
for t in range(1000): # 最多运行1000个时间步
action_probs1, state_value1 = model1(state[None, :])
action1 = tf.random.categorical(tf.math.log(action_probs1), 1)[0, 0]
action_probs2, state_value2 = model2(state[None, :])
action2 = tf.random.categorical(tf.math.log(action_probs2), 1)[0, 0]
next_state, rewards, done, _ = env.step([action1.numpy(), action2.numpy()])
next_state = tf.convert_to_tensor(next_state, dtype=tf.float32)
total_reward1 += rewards[0]
total_reward2 += rewards[1]
action_probs1_next, _ = model1(next_state[None, :])
action_probs2_next, _ = model2(next_state[None, :])
# 计算Advantage和Target
advantage1 = rewards[0] + gamma * tf.reduce_max(action_probs1_next) - state_value1
advantage2 = rewards[1] + gamma * tf.reduce_max(action_probs2_next) - state_value2
target1 = rewards[0] + gamma * tf.reduce_max(action_probs1_next)
target2 = rewards[1] + gamma * tf.reduce_max(action_probs2_next)
# 计算Actor和Critic的损失
loss_actor1 = -tf.math.log(action_probs1[0, action1]) * advantage1
loss_actor2 = -tf.math.log(action_probs2[0, action2]) * advantage2
loss_critic1 = tf.square(target1 - state_value1)
loss_critic2 = tf.square(target2 - state_value2)
# 计算总损失
total_loss1 = loss_actor1 + loss_critic1
total_loss2 = loss_actor2 + loss_critic2
# 更新参数
gradients1 = tape1.gradient(total_loss1, model1.trainable_variables)
optimizer1.apply_gradients(zip(gradients1, model1.trainable_variables))
gradients2 = tape2.gradient(total_loss2, model2.trainable_variables)
optimizer2.apply_gradients(zip(gradients2, model2.trainable_variables))
if episode % 10 == 0:
print(f"Episode: {episode}, Total Reward Agent 1: {total_reward1}, Total Reward Agent 2: {total_reward2}")
最后,我们将定义一个主函数来运行我们的多智能体系统。
if __name__ == "__main__":
# 创建多智能体环境和模型
env = MultiAgentEnv()
model1 = ActorCritic(num_actions=5)
model2 = ActorCritic(num_actions=5)
# 创建优化器
optimizer1 = tf.optimizers.Adam(learning_rate=0.001)
optimizer2 = tf.optimizers.Adam(learning_rate=0.001)
# 训练多智能体系统
train_maddpg(env, model1, model2, optimizer1, optimizer2, num_episodes=500)
通过这个示例,我们演示了如何在 OpenAI Gym 中构建一个简单的多智能体环境,并使用 MADDPG 算法对多智能体系统进行协同训练。这个示例可以作为入门多智能体强化学习的起点,同时展示了 TensorFlow 和 OpenAI Gym 在多智能体环境中的基本应用。希望这篇博客对你理解和应用多智能体系统有所帮助。