update codes

codes/HierarchicalDQN/README.md

@@ -0,0 +1,13 @@
+# Hierarchical DQN
+
+## 原理简介
+
+Hierarchical DQN是一种分层强化学习方法，与DQN相比增加了一个meta controller，
+
+![image-20210331153115575](assets/image-20210331153115575.png)
+
+即学习时，meta controller每次会生成一个goal，然后controller或者说下面的actor就会达到这个goal，直到done为止。这就相当于给agent增加了一个队长，队长擅长制定局部目标，指导agent前行，这样应对一些每回合步数较长或者稀疏奖励的问题会有所帮助。
+
+## 伪代码
+
+![image-20210331153542314](assets/image-20210331153542314.png)

codes/HierarchicalDQN/agent.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: John
+Email: johnjim0816@gmail.com
+Date: 2021-03-24 22:18:18
+LastEditor: John
+LastEditTime: 2021-05-04 22:39:34
+Discription: 
+Environment: 
+'''
+import torch
+import torch.nn as nn
+import numpy as np
+import random,math
+import torch.optim as optim
+from common.model import MLP
+from common.memory import ReplayBuffer
+
+class HierarchicalDQN:
+    def __init__(self,state_dim,action_dim,cfg):
+        self.state_dim = state_dim
+        self.action_dim = action_dim
+        self.gamma = cfg.gamma
+        self.device = cfg.device
+        self.batch_size = cfg.batch_size
+        self.frame_idx = 0 
+        self.epsilon = lambda frame_idx: cfg.epsilon_end + (cfg.epsilon_start - cfg.epsilon_end ) * math.exp(-1. * frame_idx / cfg.epsilon_decay)
+        self.policy_net = MLP(2*state_dim, action_dim,cfg.hidden_dim).to(self.device)
+        self.meta_policy_net = MLP(state_dim, state_dim,cfg.hidden_dim).to(self.device)
+        self.optimizer = optim.Adam(self.policy_net.parameters(),lr=cfg.lr)
+        self.meta_optimizer = optim.Adam(self.meta_policy_net.parameters(),lr=cfg.lr)
+        self.memory = ReplayBuffer(cfg.memory_capacity)
+        self.meta_memory = ReplayBuffer(cfg.memory_capacity)
+        self.loss_numpy  = 0
+        self.meta_loss_numpy  = 0
+        self.losses = []
+        self.meta_losses = []
+    def to_onehot(self,x):
+        oh = np.zeros(self.state_dim)
+        oh[x - 1] = 1.
+        return oh
+    def set_goal(self,state):
+        if random.random() > self.epsilon(self.frame_idx):
+            with torch.no_grad():
+                state = torch.tensor(state, device=self.device, dtype=torch.float32).unsqueeze(0)
+                goal = self.meta_policy_net(state).max(1)[1].item() 
+        else:
+            goal = random.randrange(self.state_dim)
+        return goal
+    def choose_action(self,state):
+        self.frame_idx += 1
+        if random.random() > self.epsilon(self.frame_idx):
+            with torch.no_grad():
+                state = torch.tensor(state, device=self.device, dtype=torch.float32).unsqueeze(0)
+                q_value = self.policy_net(state)
+                action = q_value.max(1)[1].item()  
+        else:
+            action = random.randrange(self.action_dim)
+        return action
+    def update(self):
+        self.update_policy()
+        self.update_meta()
+    def update_policy(self): 
+        if self.batch_size > len(self.memory):
+            return
+        state_batch, action_batch, reward_batch, next_state_batch, done_batch = self.memory.sample(self.batch_size)
+        state_batch = torch.tensor(state_batch,device=self.device,dtype=torch.float)
+        action_batch = torch.tensor(action_batch,device=self.device,dtype=torch.int64).unsqueeze(1)  
+        reward_batch = torch.tensor(reward_batch,device=self.device,dtype=torch.float)  
+        next_state_batch = torch.tensor(next_state_batch,device=self.device, dtype=torch.float)
+        done_batch = torch.tensor(np.float32(done_batch),device=self.device)
+        q_values = self.policy_net(state_batch).gather(dim=1, index=action_batch).squeeze(1)
+        next_state_values = self.policy_net(next_state_batch).max(1)[0].detach()
+        expected_q_values = reward_batch + 0.99 * next_state_values * (1-done_batch)
+        loss = nn.MSELoss()(q_values, expected_q_values) 
+        self.optimizer.zero_grad() 
+        loss.backward()
+        for param in self.policy_net.parameters():  # clip防止梯度爆炸
+            param.grad.data.clamp_(-1, 1)
+        self.optimizer.step()  
+        self.loss_numpy = loss.detach().cpu().numpy()
+        self.losses.append(self.loss_numpy)  
+    def update_meta(self):
+        if self.batch_size > len(self.meta_memory):
+            return
+        state_batch, action_batch, reward_batch, next_state_batch, done_batch = self.meta_memory.sample(self.batch_size)
+        state_batch = torch.tensor(state_batch,device=self.device,dtype=torch.float)
+        action_batch = torch.tensor(action_batch,device=self.device,dtype=torch.int64).unsqueeze(1)  
+        reward_batch = torch.tensor(reward_batch,device=self.device,dtype=torch.float)  
+        next_state_batch = torch.tensor(next_state_batch,device=self.device, dtype=torch.float)
+        done_batch = torch.tensor(np.float32(done_batch),device=self.device)
+        q_values = self.meta_policy_net(state_batch).gather(dim=1, index=action_batch).squeeze(1)
+        next_state_values = self.meta_policy_net(next_state_batch).max(1)[0].detach()
+        expected_q_values = reward_batch + 0.99 * next_state_values * (1-done_batch)
+        meta_loss = nn.MSELoss()(q_values, expected_q_values) 
+        self.meta_optimizer.zero_grad() 
+        meta_loss.backward()
+        for param in self.meta_policy_net.parameters():  # clip防止梯度爆炸
+            param.grad.data.clamp_(-1, 1)
+        self.meta_optimizer.step() 
+        self.meta_loss_numpy = meta_loss.detach().cpu().numpy()
+        self.meta_losses.append(self.meta_loss_numpy)
+
+    def save(self, path):
+        torch.save(self.policy_net.state_dict(), path+'policy_checkpoint.pth')
+        torch.save(self.meta_policy_net.state_dict(), path+'meta_checkpoint.pth')
+
+    def load(self, path):
+        self.policy_net.load_state_dict(torch.load(path+'policy_checkpoint.pth'))
+        self.meta_policy_net.load_state_dict(torch.load(path+'meta_checkpoint.pth'))
+        
+
+        
+        

codes/HierarchicalDQN/task0_train.py

@@ -0,0 +1,146 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: John
+Email: johnjim0816@gmail.com
+Date: 2021-03-29 10:37:32
+LastEditor: John
+LastEditTime: 2021-05-04 22:35:56
+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 datetime
+import numpy as np
+import torch
+import gym
+
+from common.utils import save_results,make_dir
+from common.plot import plot_rewards
+from HierarchicalDQN.agent import HierarchicalDQN
+
+curr_time = datetime.datetime.now().strftime(
+    "%Y%m%d-%H%M%S")  # obtain current time
+
+class HierarchicalDQNConfig:
+    def __init__(self):
+        self.algo = "H-DQN"  # 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  # 测试的episode数目
+        self.gamma = 0.99
+        self.epsilon_start = 1  # start epsilon of e-greedy policy
+        self.epsilon_end = 0.01
+        self.epsilon_decay = 200
+        self.lr = 0.0001  # learning rate
+        self.memory_capacity = 10000  # Replay Memory capacity
+        self.batch_size = 32
+        self.target_update = 2  # target net的更新频率
+        self.device = torch.device(
+            "cuda" if torch.cuda.is_available() else "cpu")  # 检测gpu
+        self.hidden_dim = 256  # dimension of hidden layer
+
+def env_agent_config(cfg,seed=1):
+    env = gym.make(cfg.env)  
+    env.seed(seed)
+    state_dim = env.observation_space.shape[0]
+    action_dim = env.action_space.n
+    agent = HierarchicalDQN(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):
+        state = env.reset()
+        done = False
+        ep_reward = 0
+        while not done:
+            goal = agent.set_goal(state)
+            onehot_goal = agent.to_onehot(goal)
+            meta_state = state
+            extrinsic_reward = 0
+            while not done and goal != np.argmax(state):
+                goal_state = np.concatenate([state, onehot_goal])
+                action = agent.choose_action(goal_state)
+                next_state, reward, done, _ = env.step(action)
+                ep_reward += reward
+                extrinsic_reward += reward
+                intrinsic_reward = 1.0 if goal == np.argmax(
+                    next_state) else 0.0
+                agent.memory.push(goal_state, action, intrinsic_reward, np.concatenate(
+                    [next_state, onehot_goal]), done)
+                state = next_state
+                agent.update()
+        agent.meta_memory.push(meta_state, goal, extrinsic_reward, state, done)
+        print('Episode:{}/{}, Reward:{}, Loss:{:.2f}, Meta_Loss:{:.2f}'.format(i_ep+1, cfg.train_eps, ep_reward,agent.loss_numpy ,agent.meta_loss_numpy ))
+        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.train_eps):
+        state = env.reset()
+        done = False
+        ep_reward = 0
+        while not done:
+            goal = agent.set_goal(state)
+            onehot_goal = agent.to_onehot(goal)
+            extrinsic_reward = 0
+            while not done and goal != np.argmax(state):
+                goal_state = np.concatenate([state, onehot_goal])
+                action = agent.choose_action(goal_state)
+                next_state, reward, done, _ = env.step(action)
+                ep_reward += reward
+                extrinsic_reward += reward
+                state = next_state
+                agent.update()
+        print(f'Episode:{i_ep+1}/{cfg.train_eps}, Reward:{ep_reward}, Loss:{agent.loss_numpy:.2f}, Meta_Loss:{agent.meta_loss_numpy:.2f}')
+        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
+
+if __name__ == "__main__":
+    cfg = HierarchicalDQNConfig()
+
+    # 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)
+