bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新算法模版

Browse Source
This commit is contained in:
johnjim0816
2022-11-06 12:15:36 +08:00
parent 466a17707f
commit dc78698262
256 changed files with 17282 additions and 10229 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
projects/codes/QLearning/qlearning.py
View File

@@ -5,7 +5,7 @@ Author: John
Email: johnjim0816@gmail.com
Date: 2020-09-11 23:03:00
LastEditor: John
LastEditTime: 2022-08-24 10:31:04
LastEditTime: 2022-10-30 01:38:26
Discription: use defaultdict to define Q table
Environment:
'''
@@ -16,14 +16,14 @@ from collections import defaultdict
class QLearning(object):
def __init__(self,cfg):
self.n_actions = cfg['n_actions']
self.lr = cfg['lr']
self.gamma = cfg['gamma']
self.epsilon = cfg['epsilon_start']
self.n_actions = cfg.n_actions
self.lr = cfg.lr
self.gamma = cfg.gamma
self.epsilon = cfg.epsilon_start
self.sample_count = 0
self.epsilon_start = cfg['epsilon_start']
self.epsilon_end = cfg['epsilon_end']
self.epsilon_decay = cfg['epsilon_decay']
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(self.n_actions)) # use nested dictionary to represent Q(s,a), here set all Q(s,a)=0 initially, not like pseudo code
def sample_action(self, state):
''' sample action with e-greedy policy while training