update

codes/PolicyGradient/task0_train.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: John
+Email: johnjim0816@gmail.com
+Date: 2020-11-22 23:21:53
+LastEditor: John
+LastEditTime: 2021-05-05 17:35:20
+Discription: 
+Environment: 
+'''
+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
+
+import gym
+import torch
+import datetime
+from itertools import count
+
+from PolicyGradient.agent import PolicyGradient
+from common.plot import plot_rewards
+from common.utils import save_results,make_dir
+
+curr_time = datetime.datetime.now().strftime(
+    "%Y%m%d-%H%M%S")  # obtain current time
+
+class PGConfig:
+    def __init__(self):
+        self.algo = "PolicyGradient"  # name of algo
+        self.env = 'CartPole-v0'
+        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 models
+        self.train_eps = 300 # 训练的episode数目
+        self.eval_eps = 50
+        self.batch_size = 8
+        self.lr = 0.01 # learning rate
+        self.gamma = 0.99
+        self.hidden_dim = 36 # dimmension of hidden layer
+        self.device = torch.device(
+            "cuda" if torch.cuda.is_available() else "cpu")  # check gpu
+
+
+def env_agent_config(cfg,seed=1):
+    env = gym.make(cfg.env)  
+    env.seed(seed)
+    state_dim = env.observation_space.shape[0]
+    agent = PolicyGradient(state_dim,cfg)
+    return env,agent
+
+def train(cfg,env,agent):
+    print('Start to eval !')
+    print(f'Env:{cfg.env}, Algorithm:{cfg.algo}, Device:{cfg.device}')
+    state_pool = [] # 存放每batch_size个episode的state序列
+    action_pool = []
+    reward_pool = [] 
+    rewards = []
+    ma_rewards = []
+    for i_episode in range(cfg.train_eps):
+        state = env.reset()
+        ep_reward = 0
+        for _ in count():
+            action = agent.choose_action(state) # 根据当前环境state选择action
+            next_state, reward, done, _ = env.step(action)
+            ep_reward += reward
+            if done:
+                reward = 0
+            state_pool.append(state)
+            action_pool.append(float(action))
+            reward_pool.append(reward)
+            state = next_state
+            if done:
+                print('Episode:', i_episode, ' Reward:',  ep_reward)
+                break
+        if i_episode > 0 and i_episode % cfg.batch_size == 0:
+            agent.update(reward_pool,state_pool,action_pool)
+            state_pool = [] # 每个episode的state
+            action_pool = []
+            reward_pool = []
+        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 = []
+    for i_episode in range(cfg.eval_eps):
+        state = env.reset()
+        ep_reward = 0
+        for _ in count():
+            action = agent.choose_action(state) # 根据当前环境state选择action
+            next_state, reward, done, _ = env.step(action)
+            ep_reward += reward
+            if done:
+                reward = 0
+            state = next_state
+            if done:
+                print('Episode:', i_episode, ' Reward:',  ep_reward)
+                break
+        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 = PGConfig()
+
+     # 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",
+                 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)
+