1.Actor-Critic既学习价值函数,也学习策略函数
2.价值函数用来评估当前的状态是好的,还是不好的,进而帮助Actor进行策略更新
actor_loss = torch.mean(-log_probs * td_delta.detach()) # 即由td_delta来调控损失
3.Critic的学习价值,由Q_value相同的求解方式求出,即Critic(state) = reward + Critic(next_state) * gamma
td_target = rewards + self.gamma * self.critic(next_states) * (1 - dones) td_delta = td_target - self.critic(states) # 时序差分
train.py
import gym import torch import torch.nn.functional as F import numpy as np import matplotlib.pyplot as plt import rl_utils from model import ActorCritic actor_lr = 1e-3 critic_lr = 1e-2 num_episodes = 1000 hidden_dim = 128 gamma = 0.98 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") env_name = "CartPole-v0" env = gym.make(env_name) env.seed(0) torch.manual_seed(0) state_dim = env.observation_space.shape[0] action_dim = env.action_space.n agent = ActorCritic(state_dim, hidden_dim, action_dim, actor_lr, critic_lr, gamma, device) return_list = rl_utils.train_on_policy_agent(env, agent, num_episodes) episodes_list = list(range(len(return_list))) plt.plot(episodes_list, return_list) plt.xlabel('Episodes') plt.ylabel('Returns') plt.title('Actor-Critic on {}'.format(env_name)) plt.show() mv_return = rl_utils.moving_average(return_list, 9) plt.plot(episodes_list, mv_return) plt.xlabel('Episodes') plt.ylabel('Returns') plt.title('Actor-Critic on {}'.format(env_name)) plt.show()
model.py
import torch import torch.nn.functional as F class PolicyNet(torch.nn.Module): def __init__(self, state_dim, hidden_dim, action_dim): super(PolicyNet, self).__init__() self.fc1 = torch.nn.Linear(state_dim, hidden_dim) self.fc2 = torch.nn.Linear(hidden_dim, action_dim) def forward(self, x): x = F.relu(self.fc1(x)) return F.softmax(self.fc2(x), dim=1) class ValueNet(torch.nn.Module): def __init__(self, state_dim, hidden_dim): super(ValueNet, self).__init__() self.fc1 = torch.nn.Linear(state_dim, hidden_dim) self.fc2 = torch.nn.Linear(hidden_dim, 1) def forward(self, x): x = F.relu(self.fc1(x)) return self.fc2(x) class ActorCritic: def __init__(self, state_dim, hidden_dim, action_dim, actor_lr, critic_lr, gamma, device): self.actor = PolicyNet(state_dim, hidden_dim, action_dim).to(device) self.critic = ValueNet(state_dim, hidden_dim).to(device) # 策略网络优化器 self.actor_optimizer = torch.optim.Adam(self.actor.parameters(), lr=actor_lr) self.critic_optimizer = torch.optim.Adam(self.critic.parameters(), lr=critic_lr) self.gamma = gamma self.device = device def take_action(self, state): state = torch.tensor([state], dtype=torch.float).to(self.device) probs = self.actor(state) action_dist = torch.distributions.Categorical(probs) action = action_dist.sample() return action.item() def update(self, transition_dict): states = torch.tensor(transition_dict['states'], dtype=torch.float).to(self.device) actions = torch.tensor(transition_dict['actions']).view(-1, 1).to(self.device) rewards = torch.tensor(transition_dict['rewards'], dtype=torch.float).view(-1, 1).to(self.device) next_states = torch.tensor(transition_dict['next_states'], dtype=torch.float).to(self.device) dones = torch.tensor(transition_dict['dones'], dtype=torch.float).view(-1, 1).to(self.device) # 时序差分目标 td_target = rewards + self.gamma * self.critic(next_states) * (1 - dones) td_delta = td_target - self.critic(states) # 时序差分误差 log_probs = torch.log(self.actor(states).gather(1, actions)) actor_loss = torch.mean(-log_probs * td_delta.detach()) # 即由td_delta来调控损失 # 均方误差损失函数 critic_loss = torch.mean( F.mse_loss(self.critic(states), td_target) ) self.actor_optimizer.zero_grad() self.critic_optimizer.zero_grad() actor_loss.backward() critic_loss.backward() self.actor_optimizer.step() self.critic_optimizer.step()
rl_utils.py
from tqdm import tqdm import numpy as np import torch import collections import random class ReplayBuffer: def __init__(self, capacity): self.buffer = collections.deque(maxlen=capacity) def add(self, state, action, reward, next_state, done): self.buffer.append((state, action, reward, next_state, done)) def sample(self, batch_size): transitions = random.sample(self.buffer, batch_size) state, action, reward, next_state, done = zip(*transitions) return np.array(state), action, reward, np.array(next_state), done def size(self): return len(self.buffer) def moving_average(a, window_size): cumulative_sum = np.cumsum(np.insert(a, 0, 0)) middle = (cumulative_sum[window_size:] - cumulative_sum[:-window_size]) / window_size r = np.arange(1, window_size - 1, 2) begin = np.cumsum(a[:window_size - 1])[::2] / r end = (np.cumsum(a[:-window_size:-1])[::2] / r)[::-1] return np.concatenate((begin, middle, end)) def train_on_policy_agent(env, agent, num_episodes): return_list = [] for i in range(10): with tqdm(total=int(num_episodes / 10), desc='Iteration %d' % i) as pbar: for i_episode in range(int(num_episodes / 10)): episode_return = 0 transition_dict = {'states': [], 'actions': [], 'next_states': [], 'rewards': [], 'dones': []} state = env.reset() done = False # 一局放入到一块数据里面 while not done: action = agent.take_action(state) next_state, reward, done, _ = env.step(action) transition_dict['states'].append(state) transition_dict['actions'].append(action) transition_dict['next_states'].append(next_state) transition_dict['rewards'].append(reward) transition_dict['dones'].append(done) state = next_state episode_return += reward return_list.append(episode_return) agent.update(transition_dict) if (i_episode + 1) % 10 == 0: pbar.set_postfix({'episode': '%d' % (num_episodes / 10 * i + i_episode + 1), 'return': '%.3f' % np.mean(return_list[-10:])}) pbar.update(1) return return_list def train_off_policy_agent(env, agent, num_episodes, replay_buffer, minimal_size, batch_size): return_list = [] for i in range(10): with tqdm(total=int(num_episodes / 10), desc='Iteration %d' % i) as pbar: for i_episode in range(int(num_episodes / 10)): episode_return = 0 state = env.reset() done = False while not done: action = agent.take_action(state) next_state, reward, done, _ = env.step(action) replay_buffer.add(state, action, reward, next_state, done) state = next_state episode_return += reward if replay_buffer.size() > minimal_size: b_s, b_a, b_r, b_ns, b_d = replay_buffer.sample(batch_size) transition_dict = {'states': b_s, 'actions': b_a, 'next_states': b_ns, 'rewards': b_r, 'dones': b_d} agent.update(transition_dict) return_list.append(episode_return) if (i_episode + 1) % 10 == 0: pbar.set_postfix({'episode': '%d' % (num_episodes / 10 * i + i_episode + 1), 'return': '%.3f' % np.mean(return_list[-10:])}) pbar.update(1) return return_list def compute_advantage(gamma, lmbda, td_delta): td_delta = td_delta.detach().numpy() advantage_list = [] advantage = 0.0 for delta in td_delta[::-1]: advantage = gamma * lmbda * advantage + delta advantage_list.append(advantage) advantage_list.reverse() return torch.tensor(advantage_list, dtype=torch.float)