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

hot update

Browse Source
This commit is contained in:
johnjim0816
2022-08-22 17:50:11 +08:00
parent 0a54840828
commit ad65dd17cd
54 changed files with 1639 additions and 503 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
projects/codes/DQN/task0.py
View File

@@ -1,23 +1,23 @@
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 path to system path
import gym
import torch
import datetime
import numpy as np
import argparse
from common.utils import save_results
from common.utils import save_results,all_seed
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():
""" 超参数
""" hyperparameters
"""
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
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='DQN',type=str,help="name of algorithm")
parser.add_argument('--env_name',default='CartPole-v0',type=str,help="name of environment")
@@ -33,102 +33,101 @@ def get_args():
parser.add_argument('--target_update',default=4,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('--seed',default=10,type=int,help="seed")
parser.add_argument('--result_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
'/' + curr_time + '/results/' )
'/' + curr_time + '/results' )
parser.add_argument('--model_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
'/' + curr_time + '/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
def env_agent_config(cfg,seed=1):
''' 创建环境和智能体
def env_agent_config(cfg):
''' create env and agent
'''
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"状态数：{n_states}，动作数：{n_actions}")
env = gym.make(cfg.env_name) # create env
if cfg.seed !=0: # set random seed
all_seed(env,seed=cfg.seed)
n_states = env.observation_space.shape[0] # state dimension
n_actions = env.action_space.n # action dimension
print(f"state dim: {n_states}, action dim: {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)
np.random.seed(seed)
memory = ReplayBuffer(cfg.memory_capacity) # replay buffer
agent = DQN(n_actions,model,memory,cfg) # create agent
return env, agent
def train(cfg, env, agent):
''' 训练
'''
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
print("start training!")
print(f"Env: {cfg.env_name}, Algo: {cfg.algo_name}, Device: {cfg.device}")
rewards = [] # record rewards for all episodes
steps = []
for i_ep in range(cfg.train_eps):
ep_reward = 0 # 记录一回合内的奖励
ep_reward = 0 # reward per episode
ep_step = 0
state = env.reset() # 重置环境，返回初始状态
state = env.reset() # reset and obtain initial state
while True:
ep_step += 1
action = agent.sample(state) # 选择动作
next_state, reward, done, _ = env.step(action) # 更新环境，返回transition
action = agent.sample_action(state) # sample action
next_state, reward, done, _ = env.step(action) # update env and return transitions
agent.memory.push(state, action, reward,
next_state, done) # 保存transition
state = next_state # 更新下一个状态
agent.update() # 更新智能体
ep_reward += reward # 累加奖励
next_state, done) # save transitions
state = next_state # update next state for env
agent.update() # update agent
ep_reward += reward #
if done:
break
if (i_ep + 1) % cfg.target_update == 0: # 智能体目标网络更新
if (i_ep + 1) % cfg.target_update == 0: # target net update, target_update means "C" in pseucodes
agent.target_net.load_state_dict(agent.policy_net.state_dict())
steps.append(ep_step)
rewards.append(ep_reward)
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！")
print(f'Episode: {i_ep+1}/{cfg.train_eps}, Reward: {ep_reward:.2f}: Epislon: {agent.epsilon:.3f}')
print("finish training!")
env.close()
res_dic = {'rewards':rewards}
res_dic = {'episodes':range(len(rewards)),'rewards':rewards}
return res_dic
def test(cfg, env, agent):
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
print("start testing!")
print(f"Env: {cfg.env_name}, Algo: {cfg.algo_name}, Device: {cfg.device}")
rewards = [] # record rewards for all episodes
steps = []
for i_ep in range(cfg.test_eps):
ep_reward = 0 # 记录一回合内的奖励
ep_reward = 0 # reward per episode
ep_step = 0
state = env.reset() # 重置环境，返回初始状态
state = env.reset() # reset and obtain initial state
while True:
ep_step+=1
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
action = agent.predict_action(state) # predict action
next_state, reward, done, _ = env.step(action)
state = next_state
ep_reward += reward
if done:
break
steps.append(ep_step)
rewards.append(ep_reward)
print(f'回合：{i_ep+1}/{cfg.test_eps}，奖励：{ep_reward:.2f}')
print("完成测试")
print(f'Episode: {i_ep+1}/{cfg.test_eps}，Reward: {ep_reward:.2f}')
print("finish testing!")
env.close()
return {'rewards':rewards}
return {'episodes':range(len(rewards)),'rewards':rewards}
if __name__ == "__main__":
cfg = get_args()
# 训练
# training
env, agent = env_agent_config(cfg)
res_dic = train(cfg, env, agent)
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) # 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
save_args(cfg,path = cfg.result_path) # save parameters
agent.save_model(path = cfg.model_path) # save models
save_results(res_dic, tag = 'train', path = cfg.result_path) # save results
plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "train") # plot results
# testing
env, agent = env_agent_config(cfg) # create new env for testing, sometimes can ignore this step
agent.load_model(path = cfg.model_path) # load model
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'], cfg, path = cfg.result_path,tag = "test") # 画出结果
path = cfg.result_path)
plot_rewards(res_dic['rewards'], cfg, path = cfg.result_path,tag = "test")