1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
| import random import gymnasium as gym import numpy as np import collections from tqdm import tqdm import torch import torch.nn.functional as F import matplotlib.pyplot as plt
class ReplayBuffer(object): ''' 经验回放池 ''' 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) class Qnet(torch.nn.Module): def __init__(self, state_dim, hidden_dim, action_dim): super(Qnet, 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 self.fc2(x) class DQN(object): ''' DQN算法 ''' def __init__(self, state_dim, hidden_dim, action_dim, learning_rate, gamma, epsilon, target_update, device): self.action_dim = action_dim self.q_net = Qnet(state_dim, hidden_dim, self.action_dim).to(device) self.target_q_net = Qnet(state_dim, hidden_dim, self.action_dim).to(device) self.optimizer = torch.optim.Adam(self.q_net.parameters(), lr=learning_rate) self.gamma = gamma self.epsilon = epsilon self.target_update = target_update self.count = 0 self.device = device
def take_action(self, state): if np.random.random() < self.epsilon: action = np.random.randint(self.action_dim) else: state = torch.tensor([state], dtype=torch.float).to(self.device) action = self.q_net(state).argmax().item() return action
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)
q_values = self.q_net(states).gather(1, actions) max_next_q_values = self.target_q_net(next_states).max(1)[0].view(-1, 1)
q_targets = rewards + self.gamma * max_next_q_values * (1 - dones) dqn_loss = torch.mean(F.mse_loss(q_values, q_targets)) self.optimizer.zero_grad() dqn_loss.backward() self.optimizer.step()
if self.count % self.target_update == 0: self.target_q_net.load_state_dict(self.q_net.state_dict()) self.count += 1
lr = 2e-3 num_episodes = 500 hidden_dim = 128 gamma = 0.98 epsilon = 0.01 target_update = 10 buffer_size = 10000 minimal_size = 500 batch_size = 64 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
env_name = 'CartPole-v1' env = gym.make(env_name) random.seed(0) np.random.seed(0)
torch.manual_seed(0) replay_buffer = ReplayBuffer(buffer_size) state_dim = env.observation_space.shape[0] action_dim = env.action_space.n agent = DQN(state_dim, hidden_dim, action_dim, lr, gamma, epsilon, target_update, device)
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()[0] 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)
episodes_list = list(range(len(return_list))) plt.plot(episodes_list, return_list) plt.xlabel('Episodes') plt.ylabel('Returns') plt.title('DQN on {}'.format(env_name)) plt.show()
|