hot update

projects/codes/DQN/dqn.py

@@ -5,7 +5,7 @@
 @Email: johnjim0816@gmail.com
 @Date: 2020-06-12 00:50:49
 @LastEditor: John
-LastEditTime: 2022-08-18 14:27:18
+LastEditTime: 2022-08-23 23:59:54
 @Discription: 
 @Environment: python 3.7.7
 '''
@@ -20,26 +20,26 @@ import math
 import numpy as np
 
 class DQN:
-    def __init__(self,n_actions,model,memory,cfg):
+    def __init__(self,model,memory,cfg):
 
-        self.n_actions = n_actions  
-        self.device = torch.device(cfg.device) 
-        self.gamma = cfg.gamma  
+        self.n_actions = cfg['n_actions']  
+        self.device = torch.device(cfg['device']) 
+        self.gamma = cfg['gamma']  
         ## e-greedy parameters
         self.sample_count = 0  # sample count for epsilon decay
-        self.epsilon = cfg.epsilon_start
+        self.epsilon = cfg['epsilon_start']
         self.sample_count = 0  
-        self.epsilon_start = cfg.epsilon_start
-        self.epsilon_end = cfg.epsilon_end
-        self.epsilon_decay = cfg.epsilon_decay
-        self.batch_size = cfg.batch_size
+        self.epsilon_start = cfg['epsilon_start']
+        self.epsilon_end = cfg['epsilon_end']
+        self.epsilon_decay = cfg['epsilon_decay']
+        self.batch_size = cfg['batch_size']
         self.policy_net = model.to(self.device)
         self.target_net = model.to(self.device)
         ## copy parameters from policy net to target net
         for target_param, param in zip(self.target_net.parameters(),self.policy_net.parameters()): 
             target_param.data.copy_(param.data)
         # self.target_net.load_state_dict(self.policy_net.state_dict()) # or use this to copy parameters
-        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr) 
+        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg['lr']) 
         self.memory = memory 
         self.update_flag = False 
 

projects/codes/DQN/main.py

@@ -0,0 +1,137 @@
+import sys,os
+os.environ["KMP_DUPLICATE_LIB_OK"]  =  "TRUE" # avoid "OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized."
+curr_path = os.path.dirname(os.path.abspath(__file__))  # current path
+parent_path = os.path.dirname(curr_path)  # parent path 
+sys.path.append(parent_path)  # add path to system path
+
+import gym
+import torch
+import datetime
+import numpy as np
+import argparse
+from common.utils import save_results,all_seed
+from common.utils import plot_rewards,save_args
+from common.models import MLP
+from common.memories import ReplayBuffer
+from dqn import DQN
+
+def get_args():
+    """ hyperparameters
+    """
+    curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")  # obtain current time
+    parser = argparse.ArgumentParser(description="hyperparameters")      
+    parser.add_argument('--algo_name',default='DQN',type=str,help="name of algorithm")
+    parser.add_argument('--env_name',default='CartPole-v0',type=str,help="name of environment")
+    parser.add_argument('--train_eps',default=200,type=int,help="episodes of training")
+    parser.add_argument('--test_eps',default=20,type=int,help="episodes of testing")
+    parser.add_argument('--gamma',default=0.95,type=float,help="discounted factor")
+    parser.add_argument('--epsilon_start',default=0.95,type=float,help="initial value of epsilon")
+    parser.add_argument('--epsilon_end',default=0.01,type=float,help="final value of epsilon")
+    parser.add_argument('--epsilon_decay',default=500,type=int,help="decay rate of epsilon")
+    parser.add_argument('--lr',default=0.0001,type=float,help="learning rate")
+    parser.add_argument('--memory_capacity',default=100000,type=int,help="memory capacity")
+    parser.add_argument('--batch_size',default=64,type=int)
+    parser.add_argument('--target_update',default=4,type=int)
+    parser.add_argument('--hidden_dim',default=256,type=int)
+    parser.add_argument('--device',default='cpu',type=str,help="cpu or cuda") 
+    parser.add_argument('--seed',default=10,type=int,help="seed") 
+    parser.add_argument('--show_fig',default=False,type=bool,help="if show figure or not")  
+    parser.add_argument('--save_fig',default=True,type=bool,help="if save figure or not")
+    # please manually change the following args in this script if you want
+    parser.add_argument('--result_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
+            '/' + curr_time + '/results' )
+    parser.add_argument('--model_path',default=curr_path + "/outputs/" + parser.parse_args().env_name + \
+            '/' + curr_time + '/models' )    
+    args = parser.parse_args()    
+    args = {**vars(args)}  # type(dict)         
+    return args
+
+def env_agent_config(cfg):
+    ''' create env and agent
+    '''
+    env = gym.make(cfg['env_name'])  # create env
+    if cfg['seed'] !=0: # set random seed
+        all_seed(env,seed=cfg["seed"])
+    n_states = env.observation_space.shape[0]  # state dimension
+    n_actions = env.action_space.n  # action dimension
+    print(f"n_states: {n_states}, n_actions: {n_actions}")
+    cfg.update({"n_states":n_states,"n_actions":n_actions}) # update to cfg paramters
+    model = MLP(n_states,n_actions,hidden_dim=cfg["hidden_dim"])
+    memory =  ReplayBuffer(cfg["memory_capacity"]) # replay buffer
+    agent = DQN(model,memory,cfg)  # create agent
+    return env, agent
+
+def train(cfg, env, agent):
+    ''' 训练
+    '''
+    print("start training!")
+    print(f"Env: {cfg['env_name']}, Algo: {cfg['algo_name']}, Device: {cfg['device']}")
+    rewards = []  # record rewards for all episodes
+    steps = []
+    for i_ep in range(cfg["train_eps"]):
+        ep_reward = 0  # reward per episode
+        ep_step = 0
+        state = env.reset()  # reset and obtain initial state
+        while True:
+            ep_step += 1
+            action = agent.sample_action(state)  # sample action
+            next_state, reward, done, _ = env.step(action)  # update env and return transitions
+            agent.memory.push(state, action, reward,
+                              next_state, done)  # save transitions
+            state = next_state  # update next state for env
+            agent.update()  # update agent
+            ep_reward += reward  #
+            if done:
+                break
+        if (i_ep + 1) % cfg["target_update"] == 0:  # target net update, target_update means "C" in pseucodes
+            agent.target_net.load_state_dict(agent.policy_net.state_dict())
+        steps.append(ep_step)
+        rewards.append(ep_reward)
+        if (i_ep + 1) % 10 == 0:
+            print(f'Episode: {i_ep+1}/{cfg["train_eps"]}, Reward: {ep_reward:.2f}: Epislon: {agent.epsilon:.3f}')
+    print("finish training!")
+    env.close()
+    res_dic = {'episodes':range(len(rewards)),'rewards':rewards}
+    return res_dic
+
+def test(cfg, env, agent):
+    print("start testing!")
+    print(f"Env: {cfg.env_name}, Algo: {cfg.algo_name}, Device: {cfg.device}")
+    rewards = []  # record rewards for all episodes
+    steps = []
+    for i_ep in range(cfg.test_eps):
+        ep_reward = 0  # reward per episode
+        ep_step = 0
+        state = env.reset()  # reset and obtain initial state
+        while True:
+            ep_step+=1
+            action = agent.predict_action(state)  # predict action
+            next_state, reward, done, _ = env.step(action)  
+            state = next_state  
+            ep_reward += reward 
+            if done:
+                break
+        steps.append(ep_step)
+        rewards.append(ep_reward)
+        print(f'Episode: {i_ep+1}/{cfg.test_eps}，Reward: {ep_reward:.2f}')
+    print("finish testing!")
+    env.close()
+    return {'episodes':range(len(rewards)),'rewards':rewards}
+
+
+if __name__ == "__main__":
+    cfg = get_args()
+    # training
+    env, agent = env_agent_config(cfg)
+    res_dic = train(cfg, env, agent)
+    save_args(cfg,path = cfg['result_path']) # save parameters
+    agent.save_model(path = cfg['model_path'])  # save models
+    save_results(res_dic, tag = 'train', path = cfg['result_path']) # save results
+    plot_rewards(res_dic['rewards'], cfg, path = cfg['result_path'],tag = "train")  # plot results
+    # testing
+    env, agent = env_agent_config(cfg) # create new env for testing, sometimes can ignore this step
+    agent.load_model(path = cfg['model_path'])  # load model
+    res_dic = test(cfg, env, agent)
+    save_results(res_dic, tag='test',
+                 path = cfg['result_path'])  
+    plot_rewards(res_dic['rewards'], cfg, path = cfg['result_path'],tag = "test")  

projects/codes/DQN/outputs/CartPole-v0/20220823-173936/results/params.json

@@ -0,0 +1 @@
+{"algo_name": "DQN", "env_name": "CartPole-v0", "train_eps": 200, "test_eps": 20, "gamma": 0.95, "epsilon_start": 0.95, "epsilon_end": 0.01, "epsilon_decay": 500, "lr": 0.0001, "memory_capacity": 100000, "batch_size": 64, "target_update": 4, "hidden_dim": 256, "device": "cpu", "seed": 10, "result_path": "C:\\Users\\jiangji\\Desktop\\rl-tutorials\\codes\\DQN/outputs/CartPole-v0/20220823-173936/results", "model_path": "C:\\Users\\jiangji\\Desktop\\rl-tutorials\\codes\\DQN/outputs/CartPole-v0/20220823-173936/models", "show_fig": false, "save_fig": true}

projects/codes/DQN/outputs/CartPole-v0/20220823-173936/results/testing_results.csv

@@ -0,0 +1,21 @@
+episodes,rewards
+0,200.0
+1,200.0
+2,200.0
+3,200.0
+4,200.0
+5,200.0
+6,200.0
+7,200.0
+8,200.0
+9,200.0
+10,200.0
+11,200.0
+12,200.0
+13,200.0
+14,200.0
+15,200.0
+16,200.0
+17,200.0
+18,200.0
+19,200.0

projects/codes/DQN/outputs/CartPole-v0/20220823-173936/results/training_results.csv

@@ -0,0 +1,201 @@
+episodes,rewards
+0,38.0
+1,16.0
+2,37.0
+3,15.0
+4,22.0
+5,34.0
+6,20.0
+7,12.0
+8,16.0
+9,14.0
+10,13.0
+11,21.0
+12,14.0
+13,12.0
+14,17.0
+15,12.0
+16,10.0
+17,14.0
+18,10.0
+19,10.0
+20,16.0
+21,9.0
+22,14.0
+23,13.0
+24,10.0
+25,9.0
+26,12.0
+27,12.0
+28,14.0
+29,11.0
+30,9.0
+31,8.0
+32,9.0
+33,11.0
+34,12.0
+35,10.0
+36,11.0
+37,10.0
+38,10.0
+39,18.0
+40,13.0
+41,15.0
+42,10.0
+43,9.0
+44,14.0
+45,14.0
+46,23.0
+47,17.0
+48,15.0
+49,15.0
+50,20.0
+51,28.0
+52,36.0
+53,36.0
+54,23.0
+55,27.0
+56,53.0
+57,19.0
+58,35.0
+59,62.0
+60,57.0
+61,38.0
+62,61.0
+63,65.0
+64,58.0
+65,43.0
+66,67.0
+67,56.0
+68,91.0
+69,128.0
+70,71.0
+71,126.0
+72,100.0
+73,200.0
+74,200.0
+75,200.0
+76,200.0
+77,200.0
+78,200.0
+79,200.0
+80,200.0
+81,200.0
+82,200.0
+83,200.0
+84,200.0
+85,200.0
+86,200.0
+87,200.0
+88,200.0
+89,200.0
+90,200.0
+91,200.0
+92,200.0
+93,200.0
+94,200.0
+95,200.0
+96,200.0
+97,200.0
+98,200.0
+99,200.0
+100,200.0
+101,200.0
+102,200.0
+103,200.0
+104,200.0
+105,200.0
+106,200.0
+107,200.0
+108,200.0
+109,200.0
+110,200.0
+111,200.0
+112,200.0
+113,200.0
+114,200.0
+115,200.0
+116,200.0
+117,200.0
+118,200.0
+119,200.0
+120,200.0
+121,200.0
+122,200.0
+123,200.0
+124,200.0
+125,200.0
+126,200.0
+127,200.0
+128,200.0
+129,200.0
+130,200.0
+131,200.0
+132,200.0
+133,200.0
+134,200.0
+135,200.0
+136,200.0
+137,200.0
+138,200.0
+139,200.0
+140,200.0
+141,200.0
+142,200.0
+143,200.0
+144,200.0
+145,200.0
+146,200.0
+147,200.0
+148,200.0
+149,200.0
+150,200.0
+151,200.0
+152,200.0
+153,200.0
+154,200.0
+155,200.0
+156,200.0
+157,200.0
+158,200.0
+159,200.0
+160,200.0
+161,200.0
+162,200.0
+163,200.0
+164,200.0
+165,200.0
+166,200.0
+167,200.0
+168,200.0
+169,200.0
+170,200.0
+171,200.0
+172,200.0
+173,200.0
+174,200.0
+175,200.0
+176,200.0
+177,200.0
+178,200.0
+179,200.0
+180,200.0
+181,200.0
+182,200.0
+183,200.0
+184,200.0
+185,200.0
+186,200.0
+187,200.0
+188,200.0
+189,200.0
+190,200.0
+191,200.0
+192,200.0
+193,200.0
+194,200.0
+195,200.0
+196,200.0
+197,200.0
+198,200.0
+199,200.0