深度强化学习 - CartPole 问题
Posted
技术标签:
【中文标题】深度强化学习 - CartPole 问题【英文标题】：Deep Reinforcement Learning - CartPole Problem 【发布时间】：2021-08-13 23:03:57 【问题描述】：我尝试实现最简单的深度 Q 学习算法。我认为，我已经正确地实施了它，并且知道深度 Q 学习与分歧作斗争，但回报下降得非常快，损失也在分歧。如果有人可以帮助我指出正确的超参数，或者我是否错误地实现了算法，我将不胜感激。我尝试了很多超参数组合，也改变了 QNet 的复杂性。
import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
import collections
import numpy as np
import matplotlib.pyplot as plt
import gym
from torch.nn.modules.linear import Linear
from torch.nn.modules.loss import MSELoss
class ReplayBuffer:
def __init__(self, max_replay_size, batch_size):
self.max_replay_size = max_replay_size
self.batch_size = batch_size
self.buffer = collections.deque()
def push(self, *transition):
if len(self.buffer) == self.max_replay_size:
self.buffer.popleft()
self.buffer.append(transition)
def sample_batch(self):
indices = np.random.choice(len(self.buffer), self.batch_size, replace = False)
batch = [self.buffer[index] for index in indices]
state, action, reward, next_state, done = zip(*batch)
state = np.array(state)
action = np.array(action)
reward = np.array(reward)
next_state = np.array(next_state)
done = np.array(done)
return state, action, reward, next_state, done
def __len__(self):
return len(self.buffer)
class QNet(nn.Module):
def __init__(self, state_dim, action_dim):
super(QNet, self).__init__()
self.linear1 = Linear(in_features = state_dim, out_features = 64)
self.linear2 = Linear(in_features = 64, out_features = action_dim)
def forward(self, x):
x = self.linear1(x)
x = F.relu(x)
x = self.linear2(x)
return x
def train(replay_buffer, model, target_model, discount_factor, mse, optimizer):
state, action, reward, next_state, _ = replay_buffer.sample_batch()
state, next_state = torch.tensor(state, dtype = torch.float), torch.tensor(next_state,
dtype = torch.float)
# Compute Q Value and Target Q Value
q_values = model(state).gather(1, torch.tensor(action, dtype = torch.int64).unsqueeze(-1))
with torch.no_grad():
max_next_q_values = target_model(next_state).detach().max(1)[0]
q_target_value = torch.tensor(reward, dtype = torch.float) + discount_factor *
max_next_q_values
optimizer.zero_grad()
loss = mse(q_values, q_target_value.unsqueeze(1))
loss.backward()
optimizer.step()
return loss.item()
def main():
# Define Hyperparameters and Parameters
EPISODES = 10000
MAX_REPLAY_SIZE = 10000
BATCH_SIZE = 32
EPSILON = 1.0
MIN_EPSILON = 0.05
DISCOUNT_FACTOR = 0.95
DECAY_RATE = 0.99
LEARNING_RATE = 1e-3
SYNCHRONISATION = 33
EVALUATION = 32
# Initialize Environment, Model, Target-Model, Optimizer, Loss Function and Replay Buffer
env = gym.make("CartPole-v0")
model = QNet(state_dim = env.observation_space.shape[0], action_dim =
env.action_space.n)
target_model = QNet(state_dim = env.observation_space.shape[0], action_dim =
env.action_space.n)
target_model.load_state_dict(model.state_dict())
optimizer = optim.Adam(model.parameters(), lr = LEARNING_RATE)
mse = MSELoss()
replay_buffer = ReplayBuffer(max_replay_size = MAX_REPLAY_SIZE, batch_size = BATCH_SIZE)
while len(replay_buffer) != MAX_REPLAY_SIZE:
state = env.reset()
done = False
while done != True:
action = env.action_space.sample()
next_state, reward, done, _ = env.step(action)
replay_buffer.push(state, action, reward, next_state, done)
state = next_state
# Begin with the Main Loop where the QNet is trained
count_until_synchronisation = 0
count_until_evaluation = 0
history = 'Episode': [], 'Reward': [], 'Loss': []
for episode in range(EPISODES):
total_reward = 0.0
total_loss = 0.0
state = env.reset()
iterations = 0
done = False
while done != True:
count_until_synchronisation += 1
count_until_evaluation += 1
# Take an action
if np.random.rand(1) < EPSILON:
action = env.action_space.sample()
else:
with torch.no_grad():
output = model(torch.tensor(state, dtype = torch.float)).numpy()
action = np.argmax(output)
# Observe new state and reward + store into replay_buffer
next_state, reward, done, _ = env.step(action)
total_reward += reward
replay_buffer.push(state, action, reward, next_state, done)
state = next_state
if count_until_synchronisation % SYNCHRONISATION == 0:
target_model.load_state_dict(model.state_dict())
if count_until_evaluation % EVALUATION == 0:
loss = train(replay_buffer = replay_buffer, model = model, target_model =
target_model, discount_factor = DISCOUNT_FACTOR,
mse = mse, optimizer = optimizer)
total_loss += loss
iterations += 1
print (f"Episode episode is concluded in iterations iterations with a total reward
of total_reward")
if EPSILON > MIN_EPSILON:
EPSILON *= DECAY_RATE
history['Episode'].append(episode)
history['Reward'].append(total_reward)
history['Loss'].append(total_loss)
# Plot the Loss + Reward per Episode
fig, ax = plt.subplots(figsize = (10, 6))
ax.plot(history['Episode'], history['Reward'], label = "Reward")
ax.set_xlabel('Episodes', fontsize = 15)
ax.set_ylabel('Total Reward per Episode', fontsize = 15)
plt.legend(prop = 'size': 15)
plt.show()
fig, ax = plt.subplots(figsize = (10, 6))
ax.plot(history['Episode'], history['Loss'], label = "Loss")
ax.set_xlabel('Episodes', fontsize = 15)
ax.set_ylabel('Total Loss per Episode', fontsize = 15)
plt.legend(prop = 'size': 15)
plt.show()
if __name__ == "__main__":
main()
【问题讨论】：
【参考方案1】：您的代码看起来不错，我认为您的超参数并不理想。我会改变两件事，可能是三件事：
如果我没记错的话，您每 32 步更新一次目标网络。我认为这太低了。在original paper by Mnih et al. 中，他们每 10k 步进行一次硬更新。想一想：目标网络是用来计算损失的，你基本上每 32 步更改一次损失函数，这将超过每集一次。 您的回放缓冲区非常小。我会将其设置为 100k 或 1M，即使这比您打算训练的时间长。如果重播缓冲区太小，您将丢失较旧的转换，这可能导致您的网络“忘记”它已经学到的东西。不确定这对 cartpole 有多大影响，但也许值得一试... 学习率也可能更低，我正在使用 1-e4 和 RMSProp。一般来说，更改优化器也会产生不同的结果。希望这有帮助，祝你好运:)
【讨论】：
【参考方案2】：你的代码看起来不错，写得很好，超参数看起来很合理（除了更新频率可能太低），我认为 Q 网络很小，只有一个密集层。
更深的模型可能会做得更好（虽然可能不超过 3-4 层），但您说您已经尝试了不同的网络大小。
想到的另一件事是目标更新。您每 n 步进行一次硬更新；软更新可能会有所帮助，但我不会指望它。
您也可以尝试稍微降低学习率，但我想您已经这样做了。
我的建议是：
尝试降低目标更新频率 如果您还没有尝试过更大的（更深的，例如 2/3 密集层和 32 个节点） 查看软目标更新（polyak 平均等） 在其他简单的健身房环境中尝试您的实施，并检查其行为是否仍然相同。遗憾的是，DQN 并不理想，对于很多问题不会收敛，但它应该能够解决 cartpole。
【讨论】：
以上是关于深度强化学习 - CartPole 问题的主要内容，如果未能解决你的问题，请参考以下文章
PyTorch强化学习实战——强化学习环境配置与PyTorch基础
DQN 处理 CartPole 问题——使用强化学习，本质上是训练MLP，预测每一个动作的得分
Actor-critic强化学习方法应用于CartPole-v1