强化学习实践：Policy Gradient-Cart pole 游戏展示

## 安装依赖!pip install pygame!pip install gym!pip install atari_py!pip install parlimport gymimport osimport randomimport collectionsimport paddleimport paddle.nn as nnimport numpy as npimport paddle.nn.functional as F

class PolicyGradient(nn.Layer): def __init__(self, act_dim): super(PolicyGradient, self).__init__() act_dim = act_dim        hid1_size = act_dim * 10 self.linear1 = nn.Linear(in_features=4, out_features=hid1_size) self.linear2 = nn.Linear(in_features=hid1_size, out_features=act_dim) def forward(self, obs):        out = self.linear1(obs)        out = paddle.tanh(out)        out = self.linear2(out)        out = F.softmax(out) return out

def sample(obs, MODEL): global ACTION_DIM obs = np.expand_dims(obs, axis=0) obs = paddle.to_tensor(obs, dtype='float32')    act = MODEL(obs) act_prob = np.squeeze(act, axis=0)    act = np.random.choice(range(ACTION_DIM), p=act_prob.numpy()) return actdef learn(obs, action, reward, MODEL): obs = np.array(obs).astype('float32') obs = paddle.to_tensor(obs) act_prob = MODEL(obs)    action = paddle.to_tensor(action.astype('int32')) log_prob = paddle.sum(-1.0 * paddle.log(act_prob) * F.one_hot(action, act_prob.shape[1]), axis=1)    reward = paddle.to_tensor(reward.astype('float32'))    cost = log_prob * reward    cost = paddle.sum(cost)    opt = paddle.optimizer.Adam(learning_rate=LEARNING_RATE,                                parameters=MODEL.parameters()) # 优化器(动态图) cost.backward() opt.step() opt.clear_grad() return cost.numpy()

def run_train(env, MODEL): MODEL.train() obs_list, action_list, total_reward = [], [], [] obs = env.reset() while True: # 获取随机动作和执行游戏 obs_list.append(obs)        action = sample(obs, MODEL) # 采样动作 action_list.append(action) obs, reward, isOver, info = env.step(action) total_reward.append(reward) # 结束游戏 if isOver: break return obs_list, action_list, total_rewarddef evaluate(model, env, render=False): model.eval() eval_reward = [] for i in range(5): obs = env.reset() episode_reward = 0 while True: obs = np.expand_dims(obs, axis=0) obs = paddle.to_tensor(obs, dtype='float32')            action = model(obs)            action = np.argmax(action.numpy()) obs, reward, done, _ = env.step(action) episode_reward += reward if render: env.render() if done: break eval_reward.append(episode_reward) return np.mean(eval_reward)

LEARNING_RATE = 0.001 # 学习率大小OBS_DIM = NoneACTION_DIM = None# 根据一个episode的每个step的reward列表，计算每一个Step的Gtdef calc_reward_to_go(reward_list, gamma=1.0): for i in range(len(reward_list) - 2, -1, -1): # G_t = r_t + γ·r_t+1 + ... = r_t + γ·G_t+1 reward_list[i] += gamma * reward_list[i + 1] # Gt return np.array(reward_list)def main(): global OBS_DIM global ACTION_DIM train_step_list = [] train_reward_list = [] evaluate_step_list = [] evaluate_reward_list = [] # 初始化游戏    env = gym.make('CartPole-v0') # 图像输入形状和动作维度 action_dim = env.action_space.n obs_dim = env.observation_space.shape[0]    OBS_DIM = obs_dim    ACTION_DIM = action_dim max_score = -int(1e4) # 创建存储执行游戏的内存    MODEL = PolicyGradient(ACTION_DIM)    TARGET_MODEL = PolicyGradient(ACTION_DIM) # 开始训练 print("start training...") # 训练max_episode个回合，test部分不计算入episode数量 for i in range(1000): obs_list, action_list, reward_list = run_train(env, MODEL) if i % 10 == 0: print("Episode {}, Reward Sum {}.".format(i, sum(reward_list))) batch_obs = np.array(obs_list) batch_action = np.array(action_list) batch_reward = calc_reward_to_go(reward_list)        cost = learn(batch_obs, batch_action, batch_reward, MODEL) if (i + 1) % 100 == 0: total_reward = evaluate(MODEL, env, render=False) # render=True 查看渲染效果，需要在本地运行，AIStudio无法显示 print("Test reward: {}".format(total_reward))if __name__ == '__main__': main()

W0630 11:26:18.969960 322 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.2, Runtime API Version: 11.2W0630 11:26:18.974581 322 gpu_resources.cc:91] device: 0, cuDNN Version: 8.2.start training...Episode 0, Reward Sum 37.0.Episode 10, Reward Sum 27.0.Episode 20, Reward Sum 32.0.Episode 30, Reward Sum 20.0.Episode 40, Reward Sum 18.0.Episode 50, Reward Sum 38.0.Episode 60, Reward Sum 52.0.Episode 70, Reward Sum 19.0.Episode 80, Reward Sum 27.0.Episode 90, Reward Sum 13.0.Test reward: 42.8Episode 100, Reward Sum 28.0.Episode 110, Reward Sum 44.0.Episode 120, Reward Sum 30.0.Episode 130, Reward Sum 28.0.Episode 140, Reward Sum 27.0.Episode 150, Reward Sum 47.0.Episode 160, Reward Sum 55.0.Episode 170, Reward Sum 26.0.Episode 180, Reward Sum 47.0.Episode 190, Reward Sum 17.0.Test reward: 42.8Episode 200, Reward Sum 23.0.Episode 210, Reward Sum 19.0.Episode 220, Reward Sum 15.0.Episode 230, Reward Sum 59.0.Episode 240, Reward Sum 59.0.Episode 250, Reward Sum 32.0.Episode 260, Reward Sum 58.0.Episode 270, Reward Sum 18.0.Episode 280, Reward Sum 24.0.Episode 290, Reward Sum 64.0.Test reward: 116.8Episode 300, Reward Sum 54.0.Episode 310, Reward Sum 28.0.Episode 320, Reward Sum 44.0.Episode 330, Reward Sum 18.0.Episode 340, Reward Sum 89.0.Episode 350, Reward Sum 26.0.Episode 360, Reward Sum 57.0.Episode 370, Reward Sum 54.0.Episode 380, Reward Sum 105.0.Episode 390, Reward Sum 56.0.Test reward: 94.0Episode 400, Reward Sum 70.0.Episode 410, Reward Sum 35.0.Episode 420, Reward Sum 45.0.Episode 430, Reward Sum 117.0.Episode 440, Reward Sum 50.0.Episode 450, Reward Sum 35.0.Episode 460, Reward Sum 41.0.Episode 470, Reward Sum 43.0.Episode 480, Reward Sum 75.0.Episode 490, Reward Sum 37.0.Test reward: 57.6Episode 500, Reward Sum 40.0.Episode 510, Reward Sum 85.0.Episode 520, Reward Sum 86.0.Episode 530, Reward Sum 30.0.Episode 540, Reward Sum 68.0.Episode 550, Reward Sum 25.0.Episode 560, Reward Sum 82.0.Episode 570, Reward Sum 54.0.Episode 580, Reward Sum 53.0.Episode 590, Reward Sum 58.0.Test reward: 147.2Episode 600, Reward Sum 24.0.Episode 610, Reward Sum 78.0.Episode 620, Reward Sum 62.0.Episode 630, Reward Sum 58.0.Episode 640, Reward Sum 50.0.Episode 650, Reward Sum 67.0.Episode 660, Reward Sum 68.0.Episode 670, Reward Sum 51.0.Episode 680, Reward Sum 36.0.Episode 690, Reward Sum 69.0.Test reward: 84.2Episode 700, Reward Sum 34.0.Episode 710, Reward Sum 59.0.Episode 720, Reward Sum 56.0.Episode 730, Reward Sum 72.0.Episode 740, Reward Sum 28.0.Episode 750, Reward Sum 35.0.Episode 760, Reward Sum 54.0.Episode 770, Reward Sum 61.0.Episode 780, Reward Sum 32.0.Episode 790, Reward Sum 147.0.Test reward: 123.0Episode 800, Reward Sum 129.0.Episode 810, Reward Sum 65.0.Episode 820, Reward Sum 73.0.Episode 830, Reward Sum 54.0.Episode 840, Reward Sum 60.0.Episode 850, Reward Sum 71.0.Episode 860, Reward Sum 54.0.Episode 870, Reward Sum 74.0.Episode 880, Reward Sum 34.0.Episode 890, Reward Sum 55.0.Test reward: 104.8Episode 900, Reward Sum 41.0.Episode 910, Reward Sum 111.0.Episode 920, Reward Sum 33.0.Episode 930, Reward Sum 49.0.Episode 940, Reward Sum 62.0.Episode 950, Reward Sum 114.0.Episode 960, Reward Sum 52.0.Episode 970, Reward Sum 64.0.Episode 980, Reward Sum 94.0.Episode 990, Reward Sum 90.0.Test reward: 72.2