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
2021-05-07 16:31:25 +08:00
parent 4b96f5a6b0
commit 659065e9db
161 changed files with 1963 additions and 1693 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
codes/SAC/task0_train.py
View File

@@ -5,12 +5,10 @@ Author: JiangJi
Email: johnjim0816@gmail.com
Date: 2021-04-29 12:59:22
LastEditor: JiangJi
LastEditTime: 2021-04-29 13:56:56
LastEditTime: 2021-05-06 16:58:01
Discription:
Environment:
'''
import sys,os
curr_path = os.path.dirname(__file__)
parent_path = os.path.dirname(curr_path)
@@ -36,7 +34,8 @@ class SACConfig:
self.model_path = curr_path+"/outputs/" +self.env+'/'+curr_time+'/models/' # path to save models
self.train_eps = 300
self.train_steps = 500
self.eval_eps = 50
self.eval_steps = 500
self.gamma = 0.99
self.mean_lambda=1e-3
self.std_lambda=1e-3
@@ -49,7 +48,18 @@ class SACConfig:
self.hidden_dim = 256
self.batch_size = 128
self.device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
def env_agent_config(cfg,seed=1):
env = NormalizedActions(gym.make("Pendulum-v0"))
env.seed(seed)
action_dim = env.action_space.shape[0]
state_dim = env.observation_space.shape[0]
agent = SAC(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}')
rewards = []
ma_rewards = [] # moveing average reward
for i_ep in range(cfg.train_eps):
@@ -64,25 +74,58 @@ def train(cfg,env,agent):
ep_reward += reward
if done:
break
print(f"Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward:.3f}")
if (i_ep+1)%10==0:
print(f"Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward:.3f}")
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！')
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 = [] # moveing average reward
for i_ep in range(cfg.eval_eps):
state = env.reset()
ep_reward = 0
for i_step in range(cfg.eval_steps):
action = agent.policy_net.get_action(state)
next_state, reward, done, _ = env.step(action)
state = next_state
ep_reward += reward
if done:
break
if (i_ep+1)%10==0:
print(f"Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward:.3f}")
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 evaling！')
return rewards, ma_rewards
if __name__ == "__main__":
cfg=SACConfig()
env = NormalizedActions(gym.make("Pendulum-v0"))
action_dim = env.action_space.shape[0]
state_dim = env.observation_space.shape[0]
agent = SAC(state_dim,action_dim,cfg)
rewards,ma_rewards = train(cfg,env,agent)
make_dir(cfg.result_path,cfg.model_path)
# train
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",env=cfg.env,algo = cfg.algo,path=cfg.result_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
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)