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

update

Browse Source
This commit is contained in:
johnjim0816
2021-09-15 10:32:52 +08:00
parent 95f3f4dd57
commit 5085040330
74 changed files with 431 additions and 433 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
codes/Sarsa/task0_train.py
View File

@@ -5,7 +5,7 @@ Author: John
Email: johnjim0816@gmail.com
Date: 2021-03-11 17:59:16
LastEditor: John
LastEditTime: 2021-07-15 08:52:59
LastEditTime: 2021-05-06 17:12:37
Discription:
Environment:
'''
@@ -26,8 +26,8 @@ class SarsaConfig:
''' parameters for Sarsa
'''
def __init__(self):
self.algo = 'Sarsa'
self.env = 'RacetrackEnv' # 0 up, 1 right, 2 down, 3 left
self.algo = 'Qlearning'
self.env = 'CliffWalking-v0' # 0 up, 1 right, 2 down, 3 left
self.result_path = curr_path+"/outputs/" +self.env+'/'+curr_time+'/results/' # path to save results
self.model_path = curr_path+"/outputs/" +self.env+'/'+curr_time+'/models/' # path to save models
self.train_eps = 200
@@ -52,15 +52,14 @@ def train(cfg,env,agent):
# An episode is an array of (state, action, reward) tuples
state = env.reset()
ep_reward = 0
action = agent.choose_action(state)
while True:
# for t in range(cfg.n_steps):
action = agent.choose_action(state)
next_state, reward, done = env.step(action)
ep_reward+=reward
next_action = agent.choose_action(next_state)
agent.update(state, action, reward, next_state, next_action,done)
state = next_state
action = next_action
if done:
break
if ma_rewards: