I have some troubles finding some example on the great www to how i implement a recurrent neural network with LSTM layer into my current Deep q-network in Pytorch so it become a DRQN… Bear with me i am just getting started… Futhermore, I am NOT working with images processing, thereby CNN so do not worry about this. My states are purely temperatures values.
Here is my code that i am currently train my DQN with:
# AI for Self Driving Car
#Settings to adjust inorder to get a better algorithm
# reward policy
# Less punishment to increase distance from goal
# if car is more than 10s to find goal then punish
# more hidden layers
# more hidden neurons
# gamma
# optimizer
# Importing the libraries
import numpy as np
import random # random samples from different batches (experience replay)
import os # For loading and saving brain
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim # for using stochastic gradient descent
import torch.autograd as autograd # Conversion from tensor (advanced arrays) to avoid all that contains a gradient
# We want to put the tensor into a varaible taht will also contain a
# gradient and to this we need:
from torch.autograd import Variable
# to convert this tensor into a variable containing the tensor and the gradient
# Creating the architecture of the Neural Network
class Network(nn.Module): #inherinting from nn.Module
#Self - refers to the object that will be created from this class
# - self here to specify that we're referring to the object
def __init__(self, input_size, nb_action): #[self,input neuroner, output neuroner]
super(Network, self).__init__() #inorder to use modules in torch.nn
# Input and output neurons
self.input_size = input_size
self.nb_action = nb_action
# Full connection between different layers of NN
# In this example its one input layer, one hidden layer and one output layer
# Using self here to specify that fc1 is a variable of my object
self.fc1 = nn.Linear(input_size, 40)
self.fc2 = nn.Linear(40, 30)
#Example of adding a hiddenlayer
# self.fcX = nn.Linear(30,30)
self.fc3 = nn.Linear(30, nb_action) # 30 neurons in hidden layer
# For function that will activate neurons and perform forward propagation
def forward(self, state):
# rectifier function
x = F.relu(self.fc1(state))
x = F.relu(self.fc2(x))
q_values = self.fc3(x)
return q_values
# Implementing Experience Replay
# We know that RL is based on MDP
# So going from one state(s_t) to the next state(s_t+1)
# We gonna put 100 transition between state into what we call the memory
# So we can use the distribution of experience to make a decision
class ReplayMemory(object):
def __init__(self, capacity):
self.capacity = capacity #100 transitions
self.memory = [] #memory to save transitions
# pushing transitions into memory with append
#event=transition
def push(self, event):
self.memory.append(event)
if len(self.memory) > self.capacity: #memory only contain 100 events
del self.memory[0] #delete first transition from memory if there is more that 100
# taking random sample
def sample(self, batch_size):
#Creating variable that will contain the samples of memory
#zip =reshape function if list = ((1,2,3),(4,5,6)) zip(*list)= (1,4),(2,5),(3,6)
# (state,action,reward),(state,action,reward)
samples = zip(*random.sample(self.memory, batch_size))
#This is to be able to differentiate with respect to a tensor
#and this will then contain the tensor and gradient
#so for state,action and reward we will store the seperately into some
#bytes which each one will get a gradient
#so that eventually we'll be able to differentiate each one of them
return map(lambda x: Variable(torch.cat(x, 0)), samples)
# Implementing Deep Q Learning
class Dqn():
def __init__(self, input_size, nb_action, gamma, lrate, T):
self.gamma = gamma #self.gamma gets assigned to input argument
self.T = T
# Sliding window of the evolving mean of the last 100 events/transitions
self.reward_window = []
#Creating network with network class
self.model = Network(input_size, nb_action)
#creating memory with memory class
#We gonna take 100000 samples into memory and then we will sample from this memory to
#to get a snakk number of random transitions
self.memory = ReplayMemory(100000)
#creating optimizer (stochastic gradient descent)
self.optimizer = optim.Adam(self.model.parameters(), lr = lrate) #learning rate
#input vector which is batch of input observations
#by unsqeeze we create a fake dimension to this is
#what the network expect for its inputs
#have to be the first dimension of the last_state
self.last_state = torch.Tensor(input_size).unsqueeze(0)
#Inilizing
self.last_action = 0
self.last_reward = 0
def select_action(self, state):
#Q value depends on state
#Temperature parameter T will be a positive number and the closer
#it is to ze the less sure the NN will when taking an action
#forexample
#softmax((1,2,3))={0.04,0.11,0.85} ==> softmax((1,2,3)*3)={0,0.02,0.98}
#to deactivate brain then set T=0, thereby it is full random
probs = F.softmax((self.model(Variable(state, volatile = True))*self.T),dim=1) # T=100
#create a random draw from the probability distribution created from softmax
action = probs.multinomial()
print(probs.multinomial())
return action.data[0,0]
# See section 5.3 in AI handbook
def learn(self, batch_state, batch_next_state, batch_reward, batch_action):
outputs = self.model(batch_state).gather(1, batch_action.unsqueeze(1)).squeeze(1)
#next input for target see page 7 in attached AI handbook
next_outputs = self.model(batch_next_state).detach().max(1)[0]
target = self.gamma*next_outputs + batch_reward
#Using hubble loss inorder to obtain loss
td_loss = F.smooth_l1_loss(outputs, target)
#using lass loss/error to perform stochastic gradient descent and update weights
self.optimizer.zero_grad() #reintialize the optimizer at each iteration of the loop
#This line of code that backward propagates the error into the NN
#td_loss.backward(retain_variables = True) #userwarning
td_loss.backward(retain_graph = True)
#And this line of code uses the optimizer to update the weights
self.optimizer.step()
def update(self, reward, new_signal):
#Updated one transition and we have dated the last element of the transition
#which is the new state
new_state = torch.Tensor(new_signal).float().unsqueeze(0)
self.memory.push((self.last_state, new_state, torch.LongTensor([int(self.last_action)]), torch.Tensor([self.last_reward])))
#After ending in a state its time to play a action
action = self.select_action(new_state)
if len(self.memory.memory) > 100:
batch_state, batch_next_state, batch_action, batch_reward = self.memory.sample(100)
self.learn(batch_state, batch_next_state, batch_reward, batch_action)
self.last_action = action
self.last_state = new_state
self.last_reward = reward
self.reward_window.append(reward)
if len(self.reward_window) > 1000:
del self.reward_window[0]
return action
def score(self):
return sum(self.reward_window)/(len(self.reward_window)+1.)
def save(self):
torch.save({'state_dict': self.model.state_dict(),
'optimizer' : self.optimizer.state_dict(),
}, 'last_brain.pth')
def load(self):
if os.path.isfile('last_brain.pth'):
print("=> loading checkpoint... ")
checkpoint = torch.load('last_brain.pth')
self.model.load_state_dict(checkpoint['state_dict'])
self.optimizer.load_state_dict(checkpoint['optimizer'])
print("done !")
else:
print("no checkpoint found...")
I hope there is someone to help me out there!