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

update projects

Browse Source
This commit is contained in:
johnjim0816
2022-08-15 22:31:37 +08:00
parent cd27cb67b7
commit 73948f1dc8
109 changed files with 3483 additions and 1011 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
projects/codes/DQN/task0.py
View File

@@ -1,23 +1,23 @@
import sys,os
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 torch.nn as nn
import torch.nn.functional as F
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
import gym
import torch
import datetime
import numpy as np
import argparse
from common.utils import save_results, make_dir
from common.utils import save_results
from common.utils import plot_rewards,save_args
from common.models import MLP
from common.memories import ReplayBuffer
from dqn import DQN
def get_args():
""" Hyperparameters
""" 超参数
"""
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # Obtain current time
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
parser = argparse.ArgumentParser(description="hyperparameters")
parser.add_argument('--algo_name',default='DQN',type=str,help="name of algorithm")
parser.add_argument('--env_name',default='CartPole-v0',type=str,help="name of environment")
@@ -36,7 +36,8 @@ def get_args():
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
'/' + curr_time + '/models/' )
parser.add_argument('--show_fig',default=False,type=bool,help="if show figure or not")
parser.add_argument('--save_fig',default=True,type=bool,help="if save figure or not")
args = parser.parse_args()
return args
@@ -47,8 +48,10 @@ def env_agent_config(cfg,seed=1):
env = gym.make(cfg.env_name) # 创建环境
n_states = env.observation_space.shape[0] # 状态维度
n_actions = env.action_space.n # 动作维度
print(f"n states: {n_states}, n actions: {n_actions}")
agent = DQN(n_states,n_actions, cfg) # 创建智能体
print(f"状态数：{n_states}，动作数：{n_actions}")
model = MLP(n_states,n_actions,hidden_dim=cfg.hidden_dim)
memory = ReplayBuffer(cfg.memory_capacity) # 经验回放
agent = DQN(n_actions,model,memory,cfg) # 创建智能体
if seed !=0: # 设置随机种子
torch.manual_seed(seed)
env.seed(seed)
@@ -56,12 +59,11 @@ def env_agent_config(cfg,seed=1):
return env, agent
def train(cfg, env, agent):
''' Training
''' 训练
'''
print('Start training!')
print(f'Env:{cfg.env_name}, A{cfg.algo_name}, 设备：{cfg.device}')
print("开始训练！")
print(f"回合：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{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
steps = []
for i_ep in range(cfg.train_eps):
ep_reward = 0 # 记录一回合内的奖励
@@ -69,7 +71,7 @@ def train(cfg, env, agent):
state = env.reset() # 重置环境，返回初始状态
while True:
ep_step += 1
action = agent.choose_action(state) # 选择动作
action = agent.sample(state) # 选择动作
next_state, reward, done, _ = env.step(action) # 更新环境，返回transition
agent.memory.push(state, action, reward,
next_state, done) # 保存transition
@@ -82,27 +84,17 @@ def train(cfg, env, agent):
agent.target_net.load_state_dict(agent.policy_net.state_dict())
steps.append(ep_step)
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)
if (i_ep + 1) % 1 == 0:
print(f'Episode：{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward:.2f}, Step:{ep_step:.2f} Epislon:{agent.epsilon(agent.frame_idx):.3f}')
print('Finish training!')
if (i_ep + 1) % 10 == 0:
print(f'回合：{i_ep+1}/{cfg.train_eps}，奖励：{ep_reward:.2f}，Epislon：{agent.epsilon:.3f}')
print("完成训练！")
env.close()
res_dic = {'rewards':rewards,'ma_rewards':ma_rewards,'steps':steps}
res_dic = {'rewards':rewards}
return res_dic
def test(cfg, env, agent):
print('Start testing!')
print(f'Env:{cfg.env_name}, A{cfg.algo_name}, 设备：{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
################################################################################
print("开始测试！")
print(f"回合：{cfg.env_name}, 算法：{cfg.algo_name}, 设备：{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
steps = []
for i_ep in range(cfg.test_eps):
ep_reward = 0 # 记录一回合内的奖励
@@ -110,7 +102,7 @@ def test(cfg, env, agent):
state = env.reset() # 重置环境，返回初始状态
while True:
ep_step+=1
action = agent.choose_action(state) # 选择动作
action = agent.predict(state) # 选择动作
next_state, reward, done, _ = env.step(action) # 更新环境，返回transition
state = next_state # 更新下一个状态
ep_reward += reward # 累加奖励
@@ -118,14 +110,10 @@ def test(cfg, env, agent):
break
steps.append(ep_step)
rewards.append(ep_reward)
if ma_rewards:
ma_rewards.append(ma_rewards[-1] * 0.9 + ep_reward * 0.1)
else:
ma_rewards.append(ep_reward)
print(f'Episode：{i_ep+1}/{cfg.test_eps}, Reward:{ep_reward:.2f}, Step:{ep_step:.2f}')
print('Finish testing')
print(f'回合：{i_ep+1}/{cfg.test_eps}，奖励：{ep_reward:.2f}')
print("完成测试")
env.close()
return {'rewards':rewards,'ma_rewards':ma_rewards,'steps':steps}
return {'rewards':rewards}
if __name__ == "__main__":
@@ -133,16 +121,14 @@ if __name__ == "__main__":
# 训练
env, agent = env_agent_config(cfg)
res_dic = train(cfg, env, agent)
make_dir(cfg.result_path, cfg.model_path)
save_args(cfg) # save parameters
agent.save(path=cfg.model_path) # save model
save_results(res_dic, tag='train',
path=cfg.result_path)
plot_rewards(res_dic['rewards'], res_dic['ma_rewards'], cfg, tag="train")
save_args(cfg,path = cfg.result_path) # 保存参数到模型路径上
agent.save(path = cfg.model_path) # 保存模型
save_results(res_dic, tag = 'train', path = cfg.result_path)
plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "train")
# 测试
env, agent = env_agent_config(cfg)
agent.load(path=cfg.model_path) # 导入模型
env, agent = env_agent_config(cfg) # 也可以不加，加这一行的是为了避免训练之后环境可能会出现问题，因此新建一个环境用于测试
agent.load(path = cfg.model_path) # 导入模型
res_dic = test(cfg, env, agent)
save_results(res_dic, tag='test',
path=cfg.result_path) # 保存结果
plot_rewards(res_dic['rewards'], res_dic['ma_rewards'],cfg, tag="test") # 画出结果
path = cfg.result_path) # 保存结果
plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "test") # 画出结果