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
2022-07-21 00:13:44 +08:00
parent bab7f6fe8c
commit 0f38e23baf
34 changed files with 665 additions and 422 deletions
Download Patch File Download Diff File Expand all files Collapse all files

120
codes/DoubleDQN/task0.py
View File

@@ -5,55 +5,49 @@ Author: JiangJi
Email: johnjim0816@gmail.com
Date: 2021-11-07 18:10:37
LastEditor: JiangJi
LastEditTime: 2021-12-29 15:02:30
LastEditTime: 2022-07-21 00:08:38
Discription:
'''
import sys,os
curr_path = os.path.dirname(os.path.abspath(__file__)) # 当前文件所在绝对路径
parent_path = os.path.dirname(curr_path) # 父路径
sys.path.append(parent_path) # 添加路径到系统路径
curr_path = os.path.dirname(os.path.abspath(__file__)) # current path
parent_path = os.path.dirname(curr_path) # parent path
sys.path.append(parent_path) # add to system path
import gym
import torch
import datetime
import argparse
from common.utils import save_results, make_dir
from common.utils import plot_rewards
from common.utils import save_results,make_dir
from common.utils import plot_rewards,save_args
from DoubleDQN.double_dqn import DoubleDQN
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
class Config:
def __init__(self):
################################## 环境超参数 ###################################
self.algo_name = 'DoubleDQN' # 算法名称
self.env_name = 'CartPole-v0' # 环境名称
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu") # 检测GPU
self.train_eps = 200 # 训练的回合数
self.test_eps = 30 # 测试的回合数
################################################################################
################################## 算法超参数 ###################################
self.gamma = 0.95 # 强化学习中的折扣因子
self.epsilon_start = 0.95 # e-greedy策略中初始epsilon
self.epsilon_end = 0.01 # e-greedy策略中的终止epsilon
self.epsilon_decay = 500 # e-greedy策略中epsilon的衰减率
self.lr = 0.0001 # 学习率
self.memory_capacity = 100000 # 经验回放的容量
self.batch_size = 64 # mini-batch SGD中的批量大小
self.target_update = 2 # 目标网络的更新频率
self.hidden_dim = 256 # 网络隐藏层
################################################################################
################################# 保存结果相关参数 ##############################
self.result_path = curr_path + "/outputs/" + self.env_name + \
'/' + curr_time + '/results/' # 保存结果的路径
self.model_path = curr_path + "/outputs/" + self.env_name + \
'/' + curr_time + '/models/' # 保存模型的路径
self.save = True # 是否保存图片
################################################################################
def get_args():
""" Hyperparameters
"""
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # Obtain current time
parser = argparse.ArgumentParser(description="hyperparameters")
parser.add_argument('--algo_name',default='DoubleDQN',type=str,help="name of algorithm")
parser.add_argument('--env_name',default='CartPole-v0',type=str,help="name of environment")
parser.add_argument('--train_eps',default=200,type=int,help="episodes of training")
parser.add_argument('--test_eps',default=20,type=int,help="episodes of testing")
parser.add_argument('--gamma',default=0.99,type=float,help="discounted factor")
parser.add_argument('--epsilon_start',default=0.95,type=float,help="initial value of epsilon")
parser.add_argument('--epsilon_end',default=0.01,type=float,help="final value of epsilon")
parser.add_argument('--epsilon_decay',default=500,type=int,help="decay rate of epsilon")
parser.add_argument('--lr',default=0.0001,type=float,help="learning rate")
parser.add_argument('--memory_capacity',default=100000,type=int,help="memory capacity")
parser.add_argument('--batch_size',default=64,type=int)
parser.add_argument('--target_update',default=2,type=int)
parser.add_argument('--hidden_dim',default=256,type=int)
parser.add_argument('--device',default='cpu',type=str,help="cpu or cuda")
parser.add_argument('--result_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
'/' + curr_time + '/results/' )
parser.add_argument('--model_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
'/' + curr_time + '/models/' ) # path to save models
parser.add_argument('--save_fig',default=True,type=bool,help="if save figure or not")
args = parser.parse_args()
return args
def env_agent_config(cfg,seed=1):
@@ -65,8 +59,8 @@ def env_agent_config(cfg,seed=1):
return env,agent
def train(cfg,env,agent):
print('开始训练!')
print(f'环境：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{cfg.device}')
print('Start training!')
print(f'Env:{cfg.env_name}, Algorithm:{cfg.algo_name}, Device:{cfg.device}')
rewards = [] # 记录所有回合的奖励
ma_rewards = [] # 记录所有回合的滑动平均奖励
for i_ep in range(cfg.train_eps):
@@ -84,20 +78,19 @@ def train(cfg,env,agent):
if i_ep % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
if (i_ep+1)%10 == 0:
print(f'回合：{i_ep+1}/{cfg.train_eps}，奖励：{ep_reward}')
print(f'Env:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward:.2f}')
rewards.append(ep_reward)
if ma_rewards:
ma_rewards.append(
0.9*ma_rewards[-1]+0.1*ep_reward)
else:
ma_rewards.append(ep_reward)
print('完成训练！')
env.close()
print('Finish training!')
return rewards,ma_rewards
def test(cfg,env,agent):
print('开始测试!')
print(f'环境：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{cfg.device}')
print('Start testing')
print(f'Env:{cfg.env_name}, Algorithm:{cfg.algo_name}, Device:{cfg.device}')
############# 由于测试不需要使用epsilon-greedy策略，所以相应的值设置为0 ###############
cfg.epsilon_start = 0.0 # e-greedy策略中初始epsilon
cfg.epsilon_end = 0.0 # e-greedy策略中的终止epsilon
@@ -120,25 +113,24 @@ def test(cfg,env,agent):
ma_rewards.append(ma_rewards[-1]*0.9+ep_reward*0.1)
else:
ma_rewards.append(ep_reward)
print(f"回合：{i_ep+1}/{cfg.test_eps}，奖励：{ep_reward:.1f}")
print('完成测试！')
env.close()
print(f"Epside:{i_ep+1}/{cfg.test_eps}, Reward:{ep_reward:.1f}")
print('Finish testing!')
return rewards,ma_rewards
if __name__ == "__main__":
cfg = Config()
# 训练
env, agent = env_agent_config(cfg)
cfg = get_args()
print(cfg.device)
# training
env,agent = env_agent_config(cfg,seed=1)
rewards, ma_rewards = train(cfg, env, agent)
make_dir(cfg.result_path, cfg.model_path) # 创建保存结果和模型路径的文件夹
agent.save(path=cfg.model_path) # 保存模型
save_results(rewards, ma_rewards, tag='train',
path=cfg.result_path) # 保存结果
plot_rewards(rewards, ma_rewards, cfg, tag="train") # 画出结果
# 测试
env, agent = env_agent_config(cfg)
agent.load(path=cfg.model_path) # 导入模型
rewards, ma_rewards = test(cfg, env, agent)
save_results(rewards, ma_rewards, tag='test',
path=cfg.result_path) # 保存结果
plot_rewards(rewards, ma_rewards, cfg, tag="test") # 画出结果
make_dir(cfg.result_path, cfg.model_path)
save_args(cfg)
agent.save(path=cfg.model_path)
save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)
plot_rewards(rewards, ma_rewards, cfg, tag="train")
# testing
env,agent = env_agent_config(cfg,seed=10)
agent.load(path=cfg.model_path)
rewards,ma_rewards = test(cfg,env,agent)
save_results(rewards,ma_rewards,tag = 'test',path = cfg.result_path)
plot_rewards(rewards, ma_rewards, cfg, tag="test")