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
2021-05-06 02:07:56 +08:00
parent 747f3238c0
commit b17c8f4e41
107 changed files with 1439 additions and 987 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
codes/DQN/task0_train.py
View File

@@ -5,7 +5,7 @@
@Email: johnjim0816@gmail.com
@Date: 2020-06-12 00:48:57
@LastEditor: John
LastEditTime: 2021-05-04 15:01:34
LastEditTime: 2021-05-05 16:49:15
@Discription:
@Environment: python 3.7.7
'''
@@ -14,9 +14,9 @@ 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
import datetime
import torch
import gym
import torch
import datetime
from common.utils import save_results, make_dir
from common.plot import plot_rewards
@@ -32,21 +32,21 @@ class DQNConfig:
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 results
self.train_eps = 300 # 训练的episode数目
'/'+curr_time+'/models/' # path to save models
self.train_eps = 300 # max trainng episodes
self.eval_eps = 50 # number of episodes for evaluating
self.gamma = 0.95
self.epsilon_start = 0.90 # e-greedy策略的初始epsilon
self.epsilon_start = 0.90 # start epsilon of e-greedy policy
self.epsilon_end = 0.01
self.epsilon_decay = 500
self.lr = 0.0001 # learning rate
self.memory_capacity = 100000 # Replay Memory容量
self.memory_capacity = 100000 # capacity of Replay Memory
self.batch_size = 64
self.target_update = 2 # target net的更新频率
self.target_update = 4 # update frequency of target net
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu") # 检测gpu
self.hidden_dim = 256 # 神经网络隐藏层维度
"cuda" if torch.cuda.is_available() else "cpu") # check gpu
self.hidden_dim = 256 # hidden size of net
def env_agent_config(cfg,seed=1):
env = gym.make(cfg.env)
env.seed(seed)
@@ -60,7 +60,7 @@ def train(cfg, env, agent):
print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
rewards = []
ma_rewards = [] # moveing average reward
for i_episode in range(cfg.train_eps):
for i_ep in range(cfg.train_eps):
state = env.reset()
done = False
ep_reward = 0
@@ -73,9 +73,10 @@ def train(cfg, env, agent):
agent.update()
if done:
break
if i_episode % cfg.target_update == 0:
if (i_ep+1) % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
print('Episode:{}/{}, Reward:{}'.format(i_episode+1, cfg.train_eps, ep_reward))
if (i_ep+1)%10 == 0:
print('Episode:{}/{}, Reward:{}'.format(i_ep+1, cfg.train_eps, ep_reward))
rewards.append(ep_reward)
# save ma rewards
if ma_rewards:
@@ -86,15 +87,17 @@ def train(cfg, env, agent):
return rewards, ma_rewards
def eval(cfg,env,agent):
rewards = [] # 记录所有episode的reward
ma_rewards = [] # 滑动平均的reward
print('Start to eval !')
print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
rewards = []
ma_rewards = [] # moving average rewards
for i_ep in range(cfg.eval_eps):
ep_reward = 0 # 记录每个episode的reward
state = env.reset() # 重置环境, 重新开一局（即开始新的一个episode）
ep_reward = 0 # reward per episode
state = env.reset()
while True:
action = agent.predict(state) # 根据算法选择一个动作
next_state, reward, done, _ = env.step(action) # 与环境进行一个交互
state = next_state # 存储上一个观察值
action = agent.predict(state)
next_state, reward, done, _ = env.step(action)
state = next_state
ep_reward += reward
if done:
break
@@ -103,11 +106,15 @@ def eval(cfg,env,agent):
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.eval_eps}, reward:{ep_reward:.1f}")
if (i_ep+1)%10 == 10:
print(f"Episode:{i_ep+1}/{cfg.eval_eps}, reward:{ep_reward:.1f}")
print('Complete evaling！')
return rewards,ma_rewards
if __name__ == "__main__":
cfg = DQNConfig()
# train
env,agent = env_agent_config(cfg,seed=1)
rewards, ma_rewards = train(cfg, env, agent)
make_dir(cfg.result_path, cfg.model_path)
@@ -115,7 +122,7 @@ if __name__ == "__main__":
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
env,agent = env_agent_config(cfg,seed=10)
agent.load(path=cfg.model_path)
rewards,ma_rewards = eval(cfg,env,agent)