56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
#!/usr/bin/env python
|
|
# coding=utf-8
|
|
'''
|
|
Author: John
|
|
Email: johnjim0816@gmail.com
|
|
Date: 2020-09-11 23:03:00
|
|
LastEditor: John
|
|
LastEditTime: 2021-03-26 16:51:01
|
|
Discription:
|
|
Environment:
|
|
'''
|
|
import numpy as np
|
|
import math
|
|
import torch
|
|
from collections import defaultdict
|
|
|
|
class QLearning(object):
|
|
def __init__(self,
|
|
action_dim,cfg):
|
|
self.action_dim = action_dim # dimension of acgtion
|
|
self.lr = cfg.lr # learning rate
|
|
self.gamma = cfg.gamma
|
|
self.epsilon = 0
|
|
self.sample_count = 0
|
|
self.epsilon_start = cfg.epsilon_start
|
|
self.epsilon_end = cfg.epsilon_end
|
|
self.epsilon_decay = cfg.epsilon_decay
|
|
self.Q_table = defaultdict(lambda: np.zeros(action_dim)) # A nested dictionary that maps state -> (action -> action-value)
|
|
def choose_action(self, state):
|
|
self.sample_count += 1
|
|
self.epsilon = self.epsilon_end + (self.epsilon_start - self.epsilon_end) * \
|
|
math.exp(-1. * self.sample_count / self.epsilon_decay)
|
|
# e-greedy policy
|
|
if np.random.uniform(0, 1) > self.epsilon:
|
|
action = np.argmax(self.Q_table[str(state)])
|
|
else:
|
|
action = np.random.choice(self.action_dim)
|
|
return action
|
|
|
|
def update(self, state, action, reward, next_state, done):
|
|
Q_predict = self.Q_table[str(state)][action]
|
|
if done:
|
|
Q_target = reward # terminal state
|
|
else:
|
|
Q_target = reward + self.gamma * np.max(self.Q_table[str(next_state)])
|
|
self.Q_table[str(state)][action] += self.lr * (Q_target - Q_predict)
|
|
def save(self,path):
|
|
import dill
|
|
torch.save(
|
|
obj=self.Q_table,
|
|
f=path+"Qleaning_model.pkl",
|
|
pickle_module=dill
|
|
)
|
|
def load(self, path):
|
|
import dill
|
|
self.Q_table =torch.load(f=path+'Qleaning_model.pkl',pickle_module=dill) |