策略梯度PG（ Policy Gradient） 的pytorch代碼實現示例 cart-pole遊戲

 

這段代碼是來源於這個地方：https://github.com/pytorch/examples/tree/master/reinforcement_learning

真的是非常簡單，而且巧妙地實現方法，特別有意思，特別好理解，所以在這裏和大家分享，以下是我的改進代碼，有動畫展示哦：

依賴庫：torch,gym,numpy即可

這個是train.py文件的全部，代碼，訓練結束以後，會把網絡的參數保存成pt文件

import argparse
import gym
import numpy as np
from itertools import count

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.distributions import Categorical


parser = argparse.ArgumentParser(description='PyTorch REINFORCE example')
parser.add_argument('--gamma', type=float, default=0.99, metavar='G',
                    help='discount factor (default: 0.99)')
parser.add_argument('--seed', type=int, default=543, metavar='N',
                    help='random seed (default: 543)')
parser.add_argument('--render', action='store_true',
                    help='render the environment')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                    help='interval between training status logs (default: 10)')
args = parser.parse_args()


env = gym.make('CartPole-v1')
env.seed(args.seed)
torch.manual_seed(args.seed)


class Policy(nn.Module):
    def __init__(self):
        super(Policy, self).__init__()
        self.affine1 = nn.Linear(4, 128)
        self.dropout = nn.Dropout(p=0.6)
        self.affine2 = nn.Linear(128, 2)

        self.saved_log_probs = []
        self.rewards = []

    def forward(self, x):
        x = self.affine1(x)
        x = self.dropout(x)
        x = F.relu(x)
        action_scores = self.affine2(x)
        return F.softmax(action_scores, dim=1)


policy = Policy()
optimizer = optim.Adam(policy.parameters(), lr=1e-2)
eps = np.finfo(np.float64).eps.item()


def select_action(state):
    state = torch.from_numpy(state).float().unsqueeze(0)
    probs = policy(state)
    m = Categorical(probs)
    action = m.sample()
    policy.saved_log_probs.append(m.log_prob(action))
    return action.item()


def finish_episode():
    R = 0
    policy_loss = []
    returns = []
    for r in policy.rewards[::-1]:
        R = r + args.gamma * R
        returns.insert(0, R)
    returns = torch.tensor(returns)
    returns = (returns - returns.mean()) / (returns.std() + eps)
    for log_prob, R in zip(policy.saved_log_probs, returns):
        policy_loss.append(-log_prob * R)
    optimizer.zero_grad()
    policy_loss = torch.cat(policy_loss).sum()
    policy_loss.backward()
    optimizer.step()
    del policy.rewards[:]
    del policy.saved_log_probs[:]


def main():
    running_reward = 10
    for i_episode in count(1):
        state, ep_reward = env.reset(), 0
        for t in range(1, 10000):  # Don't infinite loop while learning
            action = select_action(state)
            state, reward, done, _ = env.step(action)
            if args.render:
                env.render()
            policy.rewards.append(reward)
            ep_reward += reward
            if done:
                break

        running_reward = 0.05 * ep_reward + (1 - 0.05) * running_reward
        finish_episode()
        if i_episode % args.log_interval == 0:
            print('Episode {}\tLast reward: {:.2f}\tAverage reward: {:.2f}'.format(
                  i_episode, ep_reward, running_reward))
        if running_reward > env.spec.reward_threshold:
            print("Solved! Running reward is now {} and "
                  "the last episode runs to {} time steps!".format(running_reward, t))
            torch.save(policy.state_dict(),'hello.pt')
            break
if __name__ == '__main__':
    main()

以下是test.py文件，運行後有動畫展示：

import torch
import gym
from train import Policy
from torch.distributions import Categorical

model=Policy()
model.load_state_dict(torch.load('hello.pt'))
model.eval()

def select_action(state):
    state = torch.from_numpy(state).float().unsqueeze(0)
    probs = model(state)
    m = Categorical(probs)
    action = m.sample()
    return action.item()

env = gym.make('CartPole-v1')
t_all = []
for i_episode in range(2):
    observation = env.reset()
    for t in range(10000):
        env.render()
        cp, cv, pa, pv = observation
        action = select_action(observation)
        observation, reward, done, info = env.step(action)
        if done:
            # print("Episode finished after {} timesteps".format(t+1))
            print("倒了")
            t_all.append(t)
            break
env.close()
print(t_all)
print(sum(t_all)/len(t_all))

先運行train.py，然後再運行test.py即可

程序運行結果,這兩段代碼我仔細看了好幾遍，又不懂的，可以在評論區問我呀，應該都能回答：