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
2021-09-16 15:35:40 +08:00
parent 5085040330
commit 34fcebc4b8
31 changed files with 434 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
codes/DDPG/task0_train.py
View File

@@ -5,14 +5,14 @@
@Email: johnjim0816@gmail.com
@Date: 2020-06-11 20:58:21
@LastEditor: John
LastEditTime: 2021-05-04 14:49:45
LastEditTime: 2021-09-16 01:31:33
@Discription:
@Environment: python 3.7.7
'''
import sys,os
curr_path = os.path.dirname(__file__)
parent_path = os.path.dirname(curr_path)
sys.path.append(parent_path) # add current terminal path to sys.path
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) # 添加父路径到系统路径sys.path
import datetime
import gym
@@ -21,49 +21,45 @@ import torch
from DDPG.env import NormalizedActions, OUNoise
from DDPG.agent import DDPG
from common.utils import save_results,make_dir
from common.plot import plot_rewards
curr_time = datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S") # obtain current time
from common.plot import plot_rewards, plot_rewards_cn
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # 获取当前时间
class DDPGConfig:
def __init__(self):
self.algo = 'DDPG'
self.env = 'Pendulum-v0' # env name
self.algo = 'DDPG' # 算法名称
self.env = 'Pendulum-v0' # 环境名称
self.result_path = curr_path+"/outputs/" + self.env + \
'/'+curr_time+'/results/' # path to save results
'/'+curr_time+'/results/' # 保存结果的路径
self.model_path = curr_path+"/outputs/" + self.env + \
'/'+curr_time+'/models/' # path to save results
self.gamma = 0.99
self.critic_lr = 1e-3
self.actor_lr = 1e-4
self.memory_capacity = 10000
'/'+curr_time+'/models/' # 保存模型的路径
self.train_eps = 300 # 训练的回合数
self.eval_eps = 50 # 测试的回合数
self.gamma = 0.99 # 折扣因子
self.critic_lr = 1e-3 # 评论家网络的学习率
self.actor_lr = 1e-4 # 演员网络的学习率
self.memory_capacity = 8000
self.batch_size = 128
self.train_eps = 300
self.eval_eps = 50
self.eval_steps = 200
self.target_update = 4
self.hidden_dim = 30
self.soft_tau = 1e-2
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.target_update = 2
self.hidden_dim = 256
self.soft_tau = 1e-2 # 软更新参数
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
def env_agent_config(cfg,seed=1):
env = NormalizedActions(gym.make(cfg.env))
env.seed(seed)
env.seed(seed) # 随机种子
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.shape[0]
agent = DDPG(state_dim,action_dim,cfg)
return env,agent
def train(cfg, env, agent):
print('Start to train ! ')
print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
ou_noise = OUNoise(env.action_space) # action noise
rewards = []
ma_rewards = [] # moving average rewards
for i_episode in range(cfg.train_eps):
print('开始训练！')
print(f'环境：{cfg.env}，算法：{cfg.algo}，设备：{cfg.device}')
ou_noise = OUNoise(env.action_space) # 动作噪声
rewards = [] # 记录奖励
ma_rewards = [] # 记录滑动平均奖励
for i_ep in range(cfg.train_eps):
state = env.reset()
ou_noise.reset()
done = False
@@ -72,29 +68,29 @@ def train(cfg, env, agent):
while not done:
i_step += 1
action = agent.choose_action(state)
action = ou_noise.get_action(
action, i_step) # 即paper中的random process
action = ou_noise.get_action(action, i_step)
next_state, reward, done, _ = env.step(action)
ep_reward += reward
agent.memory.push(state, action, reward, next_state, done)
agent.update()
state = next_state
print('Episode:{}/{}, Reward:{}'.format(i_episode+1, cfg.train_eps, ep_reward))
if (i_ep+1)%10 == 0:
print('回合：{}/{}，奖励：{:.2f}'.format(i_ep+1, cfg.train_eps, ep_reward))
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('Complete training！')
print('完成训练！')
return rewards, ma_rewards
def eval(cfg, env, agent):
print('Start to Eval ! ')
print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
rewards = []
ma_rewards = [] # moving average rewards
for i_episode in range(cfg.eval_eps):
state = env.reset()
print('开始测试！')
print(f'环境：{cfg.env}, 算法：{cfg.algo}, 设备：{cfg.device}')
rewards = [] # 记录奖励
ma_rewards = [] # 记录滑动平均奖励
for i_ep in range(cfg.eval_eps):
state = env.reset()
done = False
ep_reward = 0
i_step = 0
@@ -104,32 +100,29 @@ def eval(cfg, env, agent):
next_state, reward, done, _ = env.step(action)
ep_reward += reward
state = next_state
print('Episode:{}/{}, Reward:{}'.format(i_episode+1, cfg.train_eps, ep_reward))
print('回合：{}/{}, 奖励：{}'.format(i_ep+1, cfg.train_eps, ep_reward))
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('Complete Eval！')
print('完成测试！')
return rewards, ma_rewards
if __name__ == "__main__":
cfg = DDPGConfig()
# train
# 训练
env,agent = env_agent_config(cfg,seed=1)
rewards, ma_rewards = train(cfg, env, agent)
make_dir(cfg.result_path, cfg.model_path)
agent.save(path=cfg.model_path)
save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)
plot_rewards(rewards, ma_rewards, tag="train",
algo=cfg.algo, path=cfg.result_path)
# eval
plot_rewards_cn(rewards, ma_rewards, tag="train", env = cfg.env, algo=cfg.algo, path=cfg.result_path)
# 测试
env,agent = env_agent_config(cfg,seed=10)
agent.load(path=cfg.model_path)
rewards,ma_rewards = eval(cfg,env,agent)
save_results(rewards,ma_rewards,tag='eval',path=cfg.result_path)
plot_rewards(rewards,ma_rewards,tag="eval",env=cfg.env,algo = cfg.algo,path=cfg.result_path)
save_results(rewards,ma_rewards,tag = 'eval',path = cfg.result_path)
plot_rewards_cn(rewards,ma_rewards,tag = "eval",env = cfg.env,algo = cfg.algo,path=cfg.result_path)